Example meta information file for Task 1 baseline system task1/Schmid_CPJKU_task1_1/Schmid_CPJKU_task1_1.meta.yaml:

# Submission information
submission:
  # Submission label
  # Label is used to index submissions.
  # Generate your label following way to avoid
  # overlapping codes among submissions:
  # [Last name of corresponding author]_[Abbreviation of institute of the corresponding author]_task[task number]_[index number of your submission (1-3)]
  label: Schmid_CPJKU_task1_1

  # Submission name
  # This name will be used in the results tables when space permits
  name: DCASE2024 baseline system

  # Submission name abbreviated
  # This abbreviated name will be used in the results table when space is tight.
  # Use maximum 10 characters.
  abbreviation: Baseline

  # Authors of the submitted system. Mark authors in
  # the order you want them to appear in submission lists.
  # One of the authors has to be marked as corresponding author,
  # this will be listed next to the submission in the results tables.
  authors:
    # First author
    - lastname: Schmid
      firstname: Florian
      email: florian.schmid@jku.at           # Contact email address
      corresponding: true                    # Mark true for one of the authors
      # Affiliation information for the author
      affiliation:
        abbreviation: JKU
        institute: Johannes Kepler University (JKU) Linz
        department: Institute of Computational Perception (CP)   # Optional
        location: Linz, Austria

    # Second author
    - lastname: Primus
      firstname: Paul
      email: paul.primus@jku.at   
      affiliation:
        abbreviation: JKU
        institute: Johannes Kepler University (JKU) Linz
        department: Institute of Computational Perception (CP)  
        location: Linz, Austria      

    # Third author
    - lastname: Heittola
      firstname: Toni
      email: toni.heittola@tuni.fi
      affiliation:
        abbreviation: TAU
        institute: Tampere University
        department: Computing Sciences            
        location: Tampere, Finland
    
    # Fourth author
    - lastname: Mesaros
      firstname: Annamaria
      email: annamaria.mesaros@tuni.fi
      affiliation:
        abbreviation: TAU
        institute: Tampere University
        department: Computing Sciences            
        location: Tampere, Finland
    
    # Fifth author
    - lastname: Martín Morató
      firstname: Irene
      email: irene.martinmorato@tuni.fi
      affiliation:
        abbreviation: TAU
        institute: Tampere University
        department: Computing Sciences           
        location: Tampere, Finland

    # Sixth author
    - lastname: Koutini
      firstname: Khaled
      email: khaled.koutini@jku.at     
      affiliation:
        abbreviation: JKU
        institute: Johannes Kepler University (JKU) Linz
        department: Institute of Computational Perception (CP)  
        location: Linz, Austria

    # Seventh author
    - lastname: Widmer
      firstname: Gerhard
      email: gerhard.widmer@jku.at
      affiliation:
        abbreviation: JKU
        institute: Johannes Kepler University (JKU) Linz
        department: Institute of Computational Perception (CP)  
        location: Linz, Austria           

# System information
system:
  # System description, meta data provided here will be used to do
  # meta analysis of the submitted system.
  # Use general level tags, when possible use the tags provided in comments.
  # If information field is not applicable to the system, use "!!null".
  description:

    # Audio input / sampling rate
    # e.g. 16kHz, 22.05kHz, 32kHz, 44.1kHz, 48.0kHz
    input_sampling_rate: 32kHz

    # Acoustic representation
    # one or multiple labels, e.g. MFCC, log-mel energies, spectrogram, CQT, raw waveform, ...
    acoustic_features: log-mel energies

    # Data augmentation methods
    # e.g. mixup, freq-mixstyle, dir augmentation, pitch shifting, time rolling, frequency masking, time masking, frequency warping, ...
    data_augmentation: freq-mixstyle, pitch shifting, time rolling

    # Machine learning
    # e.g., (RF-regularized) CNN, RNN, CRNN, Transformer, ...
    machine_learning_method: RF-regularized CNN

    # External data usage method
    # e.g. "dataset", "embeddings", "pre-trained model", ...
    external_data_usage: !!null

    # Method for handling the complexity restrictions
    # e.g. "knowledge distillation", "pruning", "precision_16", "weight quantization", "network design", ...
    complexity_management: precision_16, network design

    # System training/processing pipeline stages
    # e.g. "train teachers", "ensemble teachers", "train student using knowledge distillation", "quantization-aware training"
    pipeline: training

    # Machine learning framework
    # e.g. keras/tensorflow, pytorch, ...
    framework: pytorch

    # List all basic hyperparameters that were adapted for the different subsets (or leave !!null in case no adaptations were made)
    # e.g. "lr", "epochs", "batch size", "weight decay", "freq-mixstyle probability", "frequency mask size", "time mask size", 
    #      "time rolling range", "dir augmentation probability", ...
    split_adaptations: !!null

    # List most important properties that make this system different from other submitted systems (or leave !!null if you submit only one system)
    # e.g. "architecture", "model size", "input resolution", "data augmentation techniques", "pre-training", "knowledge distillation", ...
    system_adaptations: !!null

  # System complexity
  complexity:
    # Total model size in bytes. Calculated as [parameter count]*[bit per parameter]/8
    total_model_size: 122296  # 61,148 * 16 bits = 61,148 * 2 B = 122,296 B for the baseline system

    # Total amount of parameters used in the acoustic model.
    # For neural networks, this information is usually given before training process
    # in the network summary.
    # For other than neural networks, if parameter count information is not directly
    # available, try estimating the count as accurately as possible.
    # In case of ensemble approaches, add up parameters for all subsystems.
    # In case embeddings are used, add up parameter count of the embedding
    # extraction networks and classification network
    # Use numerical value.
    total_parameters: 61148 

    # MACS - as calculated by NeSsi
    macs: 29419156

  # List of external datasets used in the submission.
  external_datasets:
    # Below are two examples (NOT used in the baseline system)
    #- name: EfficientAT
    #  url: https://github.com/fschmid56/EfficientAT
    #  total_audio_length: !!null
    #- name: MicIRP
    #  url: http://micirp.blogspot.com/?m=1
    #  total_audio_length: 2   # specify in minutes

  # URL to the source code of the system [optional]
  source_code: https://github.com/CPJKU/dcase2024_task1_baseline

# System results
results:
  development_dataset:
    # System results on the development-test set for all provided data splits (5%, 10%, 25%, 50%, 100%).
    # Full results are not mandatory, however, they are highly recommended
    # as they are needed for through analysis of the challenge submissions.
    # If you are unable to provide all results, also incomplete
    # results can be reported.

    split_5:  # results on 5% subset
      # Overall metrics
      overall:
        logloss: !!null   # !!null, if you don't have the corresponding result
        accuracy: 42.4    # mean of class-wise accuracies

      # Class-wise metrics
      class_wise:
        airport:
          logloss: !!null  # !!null, if you don't have the corresponding result
          accuracy: 34.77
        bus:
          logloss: !!null
          accuracy: 45.21
        metro:
          logloss: !!null
          accuracy: 30.79
        metro_station:
          logloss: !!null
          accuracy: 40.03
        park:
          logloss: !!null
          accuracy: 62.06
        public_square:
          logloss: !!null
          accuracy: 22.28
        shopping_mall:
          logloss: !!null
          accuracy: 52.07
        street_pedestrian:
          logloss: !!null
          accuracy: 31.32
        street_traffic:
          logloss: !!null
          accuracy: 70.23
        tram:
          logloss: !!null
          accuracy: 35.20

      # Device-wise
      device_wise:
        a:
          logloss: !!null
          accuracy: 54.45
        b:
          logloss: !!null
          accuracy: 45.73
        c:
          logloss: !!null
          accuracy: 48.42
        s1:
          logloss: !!null
          accuracy: 39.66
        s2:
          logloss: !!null
          accuracy: 36.13
        s3:
          logloss: !!null
          accuracy: 44.30
        s4:
          logloss: !!null
          accuracy: 38.90
        s5:
          logloss: !!null
          accuracy: 40.47
        s6:
          logloss: !!null
          accuracy: 33.58

    split_10: # results on 10% subset
      # Overall metrics
      overall:
        logloss: !!null
        accuracy: 45.29    # mean of class-wise accuracies

      # Class-wise metrics
      class_wise:
        airport:
          logloss: !!null
          accuracy: 38.50
        bus:
          logloss: !!null
          accuracy: 47.99
        metro:
          logloss: !!null
          accuracy: 36.93
        metro_station:
          logloss: !!null
          accuracy: 43.71
        park:
          logloss: !!null
          accuracy: 65.43
        public_square:
          logloss: !!null
          accuracy: 27.05
        shopping_mall:
          logloss: !!null
          accuracy: 52.46
        street_pedestrian:
          logloss: !!null
          accuracy: 31.82
        street_traffic:
          logloss: !!null
          accuracy: 72.64
        tram:
          logloss: !!null
          accuracy: 36.41

      # Device-wise
      device_wise:
        a:
          logloss: !!null
          accuracy: 57.84                        
        b:
          logloss: !!null
          accuracy: 48.60
        c:
          logloss: !!null
          accuracy: 51.13
        s1:
          logloss: !!null
          accuracy: 42.16
        s2:
          logloss: !!null
          accuracy: 40.30
        s3:
          logloss: !!null
          accuracy: 46.00
        s4:
          logloss: !!null
          accuracy: 43.13
        s5:
          logloss: !!null
          accuracy: 41.30
        s6:
          logloss: !!null
          accuracy: 37.26

    split_25:  # results on 25% subset
      # Overall metrics
      overall:
        logloss: !!null
        accuracy: 50.29    # mean of class-wise accuracies

      # Class-wise metrics
      class_wise:
        airport:
          logloss: !!null
          accuracy: 41.81                           
        bus:
          logloss: !!null
          accuracy: 61.19
        metro:
          logloss: !!null
          accuracy: 38.88
        metro_station:
          logloss: !!null
          accuracy: 40.84
        park:
          logloss: !!null
          accuracy: 69.74
        public_square:
          logloss: !!null
          accuracy: 33.54
        shopping_mall:
          logloss: !!null
          accuracy: 58.84
        street_pedestrian:
          logloss: !!null
          accuracy: 30.31
        street_traffic:
          logloss: !!null
          accuracy: 75.93
        tram:
          logloss: !!null
          accuracy: 51.77

      # Device-wise
      device_wise:
        a:
          logloss: !!null
          accuracy: 62.27                        
        b:
          logloss: !!null
          accuracy: 53.27
        c:
          logloss: !!null
          accuracy: 55.39
        s1:
          logloss: !!null
          accuracy: 47.52
        s2:
          logloss: !!null
          accuracy: 46.68
        s3:
          logloss: !!null
          accuracy: 51.59
        s4:
          logloss: !!null
          accuracy: 47.39
        s5:
          logloss: !!null
          accuracy: 46.75
        s6:
          logloss: !!null
          accuracy: 41.75

    split_50: # results on 50% subset
      # Overall metrics
      overall:
        logloss: !!null
        accuracy: 53.19    # mean of class-wise accuracies

      # Class-wise metrics
      class_wise:
        airport:
          logloss: !!null
          accuracy: 41.51                         
        bus:
          logloss: !!null
          accuracy: 63.23
        metro:
          logloss: !!null
          accuracy: 43.37
        metro_station:
          logloss: !!null
          accuracy: 48.71
        park:
          logloss: !!null
          accuracy: 72.55
        public_square:
          logloss: !!null
          accuracy: 34.25
        shopping_mall:
          logloss: !!null
          accuracy: 60.09
        street_pedestrian:
          logloss: !!null
          accuracy: 37.26
        street_traffic:
          logloss: !!null
          accuracy: 79.71
        tram:
          logloss: !!null
          accuracy: 51.16

      # Device-wise
      device_wise:
        a:
          logloss: !!null
          accuracy: 65.39                        
        b:
          logloss: !!null
          accuracy: 56.30
        c:
          logloss: !!null
          accuracy: 57.23
        s1:
          logloss: !!null
          accuracy: 52.99
        s2:
          logloss: !!null
          accuracy: 50.85
        s3:
          logloss: !!null
          accuracy: 54.78
        s4:
          logloss: !!null
          accuracy: 48.35
        s5:
          logloss: !!null
          accuracy: 47.93
        s6:
          logloss: !!null
          accuracy: 44.90

    split_100:  # results on 100% subset
      # Overall metrics
      overall:
        logloss: !!null
        accuracy: 56.99    # mean of class-wise accuracies

      # Class-wise metrics
      class_wise:
        airport:
          logloss: !!null
          accuracy: 46.45
        bus:
          logloss: !!null
          accuracy: 72.95
        metro:
          logloss: !!null
          accuracy: 52.86
        metro_station:
          logloss: !!null
          accuracy: 41.56
        park:
          logloss: !!null
          accuracy: 76.11
        public_square:
          logloss: !!null
          accuracy: 37.07
        shopping_mall:
          logloss: !!null
          accuracy: 66.91
        street_pedestrian:
          logloss: !!null
          accuracy: 38.73
        street_traffic:
          logloss: !!null
          accuracy: 80.66
        tram:
          logloss: !!null
          accuracy: 56.58

      # Device-wise
      device_wise:
        a:
          logloss: !!null
          accuracy: 67.17                        
        b:
          logloss: !!null
          accuracy: 59.67
        c:
          logloss: !!null
          accuracy: 61.99
        s1:
          logloss: !!null
          accuracy: 56.28
        s2:
          logloss: !!null
          accuracy: 55.69
        s3:
          logloss: !!null
          accuracy: 58.16
        s4:
          logloss: !!null
          accuracy: 53.05
        s5:
          logloss: !!null
          accuracy: 52.35
        s6:
          logloss: !!null
          accuracy: 48.58

Example meta information file for Task 2 baseline system task2/Nishida_HIT_task2_1/Nishida_HIT_task2_1.meta.yaml:

# Submission information
submission:
  # Submission label
  # Label is used to index submissions.
  # Generate your label following way to avoid overlapping codes among submissions:
  # [Last name of corresponding author]_[Abbreviation of institute of the corresponding author]_task[task number]_[index number of your submission (1-4)]
  label: Nishida_HIT_task2_1

  # Submission name
  # This name will be used in the results tables when space permits.
  name: DCASE2024 baseline system

  # Submission name abbreviated
  # This abbreviated name will be used in the results table when space is tight.
  # Use a maximum of 10 characters.
  abbreviation: Baseline

  # Authors of the submitted system.
  # Mark authors in the order you want them to appear in submission lists.
  # One of the authors has to be marked as corresponding author, this will be listed next to the submission in the results tables.
  authors:
    # First author
    - firstname: Tomoya
      lastname: Nishida
      email: tomoya.nishida.ax@hitachi.com # Contact email address
      corresponding: true # Mark true for one of the authors

      # Affiliation information for the author
      affiliation:
        institution: Hitachi, Ltd.
        department: Research and Development Group # Optional
        location: Tokyo, Japan

    # Second author
    - firstname: Noboru
      lastname: Harada
      email: noboru@ieee.org

      # Affiliation information for the author
      affiliation:
        institution: NTT Corporation
        location: Kanagawa, Japan

    # Third author
    - firstname: Daisuke
      lastname: Niizumi
      email: daisuke.niizumi.dt@hco.ntt.co.jp

      # Affiliation information for the author
      affiliation:
        institution: NTT Corporation
        location: Kanagawa, Japan


# System information
system:
  # System description, metadata provided here will be used to do a meta-analysis of the submitted system.
  # Use general level tags, when possible use the tags provided in comments.
  # If information field is not applicable to the system, use "!!null".
  description:
    # Audio input
    # Please specify all sampling rates (comma-separated list).
    # e.g. 16kHz, 22.05kHz, 44.1kHz
    input_sampling_rate: 16kHz

    # Data augmentation methods
    # Please specify all methods used (comma-separated list).
    # e.g. mixup, time stretching, block mixing, pitch shifting, ...
    data_augmentation: !!null

    # Front-end (preprocessing) methods
    # Please specify all methods used (comma-separated list).
    # e.g. HPSS, WPE, NMF, NN filter, RPCA, ...
    front_end: !!null

    # Acoustic representation
    # one or multiple labels, e.g. MFCC, log-mel energies, spectrogram, CQT, raw waveform, ...
    acoustic_features: log-mel energies

    # Embeddings
    # Please specify all pre-trained embedings used (comma-separated list).
    # one or multiple, e.g. VGGish, OpenL3, ...
    embeddings: !!null

    # Machine learning
    # In case using ensemble methods, please specify all methods used (comma-separated list).
    # e.g. AE, VAE, GAN, GMM, k-means, OCSVM, normalizing flow, CNN, LSTM, random forest, ensemble, ...
    machine_learning_method: AE

    # Method for aggregating predictions over time
    # Please specify all methods used (comma-separated list).
    # e.g. average, median, maximum, minimum, ...
    aggregation_method: average

    # Method for domain generalizatoin and domain adaptation
    # Please specify all methods used (comma-separated list).
    # e.g. fine-tuning, invariant feature extraction, ...
    domain_adaptation_method: !!null
    domain_generalization_method: !!null

    # Ensemble method subsystem count
    # In case ensemble method is not used, mark !!null.
    # e.g. 2, 3, 4, 5, ...
    ensemble_method_subsystem_count: !!null

    # Decision making in ensemble
    # e.g. average, median, maximum, minimum, ...
    decision_making: !!null

    # Usage of the attribute information in the file names and attribute csv files
    # Please specify all usages (comma-separated list).
    # e.g. interpolation, extrapolation, condition ...
    attribute_usage: !!null

    # External data usage method
    # Please specify all usages (comma-separated list).
    # e.g. simulation of anomalous samples, embeddings, pre-trained model, ...
    external_data_usage: !!null

    # Usage of the development dataset
    # Please specify all usages (comma-separated list).
    # e.g. development, pre-training, fine-tuning
    development_data_usage: development

  # System complexity, metadata provided here may be used to evaluate submitted systems from the computational load perspective.
  complexity:
    # Total amount of parameters used in the acoustic model.
    # For neural networks, this information is usually given before training process in the network summary.
    # For other than neural networks, if parameter count information is not directly available, try estimating the count as accurately as possible.
    # In case of ensemble approaches, add up parameters for all subsystems.
    # In case embeddings are used, add up parameter count of the embedding extraction networks and classification network.
    # Use numerical value.
    total_parameters: 269992

  # List of external datasets used in the submission.
  # Development dataset is used here only as an example, list only external datasets
  external_datasets:
    # Dataset name
    - name: DCASE 2024 Challenge Task 2 Development Dataset

      # Dataset access URL
      url: https://zenodo.org/records/10902294

  # URL to the source code of the system [optional, highly recommended]
  # Reproducibility will be used to evaluate submitted systems.
  source_code: https://github.com/nttcslab/dcase2023_task2_baseline_ae

# System results
results:
  development_dataset:
    # System results for development dataset.
    # Full results are not mandatory, however, they are highly recommended as they are needed for a thorough analysis of the challenge submissions.
    # If you are unable to provide all results, also incomplete results can be reported.

    # AUC for all domains [%]
    # No need to round numbers
    ToyCar:
      auc_source: 66.98
      auc_target: 33.75
      pauc: 48.77

    ToyTrain:
      auc_source: 76.63
      auc_target: 46.92
      pauc: 47.95

    bearing:
      auc_source: 62.01
      auc_target: 61.40
      pauc: 57.58

    fan:
      auc_source: 67.71
      auc_target: 55.24
      pauc: 57.53

    gearbox:
      auc_source: 70.40
      auc_target: 69.34
      pauc: 55.65

    slider:
      auc_source: 66.51
      auc_target: 56.01
      pauc: 51.77

    valve:
      auc_source: 51.07
      auc_target: 46.25
      pauc: 52.42

Example meta information file for Task 3 baseline system task3/Politis_TAU_task3a_1/Politis_TAU_task3a_1.meta.yaml:

# Submission information
submission:
  # Submission label
  # Label is used to index submissions, to avoid overlapping codes among submissions
  # use following way to form your label:
  # [Last name of corresponding author]_[Abbreviation of institute of the corresponding author]_task[task number]_[index number of your submission (1-4)]
  label: Politis_TAU_task3a_1

  # Submission name
  # This name will be used in the results tables when space permits
  name: DCASE2024 Audio-only Ambisonic baseline

  # Submission name abbreviated
  # This abbreviated name will be used in the results table when space is tight, maximum 10 characters
  abbreviation: FOA_AO_base

  # Submission authors in order, mark one of the authors as corresponding author.
  authors:
    # First author
    - lastname: Politis
      firstname: Archontis
      email: archontis.politis@tuni.fi                  # Contact email address
      corresponding: true                             	# Mark true for one of the authors

      # Affiliation information for the author
      affiliation:
        abbreviation: TAU
        institute: Tampere University
        department: Audio Research Group
        location: Tampere, Finland

    # Second author
    - lastname: Shimada
      firstname: Kazuki
      email: kazuki.shimada@sony.com                   # Contact email address

      # Affiliation information for the author
      affiliation:
        abbreviation: SONY
        institute: SONY
        department:
        location: Tokyo, Japan


# System information
system:
  # System description, meta data provided here will be used to do
  # meta analysis of the submitted system. Use general level tags, if possible use the tags provided in comments.
  # If information field is not applicable to the system, use "!!null".
  description:
  
    # Model type (audio-only or audiovisual track)
    model_type: Audio                       # Audio or Audiovisual

    # Audio input
    input_format: Ambisonic                 # Ambisonic or Microphone Array or both
    input_sampling_rate: 24kHz

    # Acoustic representation
    acoustic_features: mel spectra, intensity vector   # e.g one or multiple [phase and magnitude spectra, mel spectra, GCC-PHAT, TDOA, intensity vector ...]
    visual_features: !!null

    # Data augmentation methods
    data_augmentation: !!null             	# [time stretching, block mixing, pitch shifting, ...]

    # Machine learning
    # In case of using ensemble methods, please specify all methods used (comma separated list).
    machine_learning_method: CRNN, MHSA     # e.g one or multiple [GMM, HMM, SVM, kNN, MLP, CNN, RNN, CRNN, NMF, MHSA, random forest, ensemble, ...]
    
    #List external datasets in case of use for training
    external_datasets:  !!null              #AudioSet, ImageNet...

    #List here pre-trained models in case of use
    pre_trained_models: !!null              #AST, PANNs...


  # System complexity, meta data provided here will be used to evaluate
  # submitted systems from the computational load perspective.
  complexity:

    # Total amount of parameters used in the acoustic model. For neural networks, this
    # information is usually given before training process in the network summary.
    # For other than neural networks, if parameter count information is not directly available,
    # try estimating the count as accurately as possible.
    # In case of ensemble approaches, add up parameters for all subsystems.
    total_parameters: 500000

  # URL to the source code of the system [optional]
  source_code: https://github.com/partha2409/DCASE2024_seld_baseline

# System results
results:

  development_dataset:
    # System result for development dataset on the provided testing split.

    # Overall score 
    overall:
      F_20_1: 13.1
      DOAE: 36.9
      RDE: 0.33

Example meta information file for Task 4 baseline system task4/Cornell_CMU_task4_1/Cornell_CMU_task4_1.meta.yaml:

# Submission information
submission:
  # Submission label
  # Label is used to index submissions, to avoid overlapping codes among submissions
  # use following way to form your label:
  # [Last name of corresponding author]_[Abbreviation of institute of the corresponding author]_task[task number]_[index number of your submission (1-4)]
  label: Cornell_CMU_task4_1

  # Submission name
  # This name will be used in the results tables when space permits
  name: DCASE2024 baseline system

  # Submission name abbreviated
  # This abbreviated name will be used in the results table when space is tight, maximum 10 characters
  abbreviation: Baseline

  # Submission authors in order, mark one of the authors as corresponding author.
  authors:
    # First author
    - lastname: Cornell
      firstname: Samuele
      email: cornellsamuele@gmail.com                 # Contact email address
      corresponding: true                             # Mark true for one of the authors

      # Affiliation information for the author
      affiliation:
        abbreviation: CMU
        institute: Carnegie Mellon University
        department: Language Technologies Institute
        location: Pittsburgh, PA, United States

    # Second author
    - lastname: Ebbers
      firstname: Janek
      email: ebbers@merl.com                  # Contact email address


      # Affiliation information for the author
      affiliation:
        abbreviation: MERL
        institute: Mitsubishi Electric Research Laboratories
        department: Speech & Audio
        location: Cambridge, MA, United States

    #...



# System information
system:
  # System description, meta data provided here will be used to do
  # meta analysis of the submitted system. Use general level tags, if possible use the tags provided in comments.
  # If information field is not applicable to the system, use "!!null".
  description:

    # Audio input
    input_channels: mono                  # e.g. one or multiple [mono, binaural, left, right, mixed, ...]
    input_sampling_rate: 16               # In kHz

    # Acoustic representation
    acoustic_features: log-mel energies   # e.g one or multiple [MFCC, log-mel energies, spectrogram, CQT, ...]

    # Data augmentation methods
    data_augmentation: !!null             # [time stretching, block mixing, pitch shifting, ...]

    # Machine learning
    # In case using ensemble methods, please specify all methods used (comma separated list).
    machine_learning_method: CRNN      # e.g one or multiple [GMM, HMM, SVM, kNN, MLP, CNN, RNN, CRNN, NMF, random forest, ensemble, ...]

    # Ensemble method subsystem count
    # In case ensemble method is not used, mark !!null.
    ensemble_method_subsystem_count: !!null # [2, 3, 4, 5, ... ]

    # Decision making methods
    decision_making: !!null                 # [majority vote, ...]

    # Semi-supervised method used to exploit both labelled and unlabelled data
    machine_learning_semi_supervised: mean-teacher student         # e.g one or multiple [pseudo-labelling, mean-teacher student...]

    # Segmentation method
    segmentation_method: !!null					            # E.g. [RBM, attention layers...]

    # Post-processing
    post-processing: median filtering       				# [median filtering, time aggregation...]

  # System complexity, meta data provided here will be used to evaluate
  # submitted systems from the computational load perspective.
  complexity:

    # Total amount of parameters used in the acoustic model. For neural networks, this
    # information is usually given before training process in the network summary.
    # For other than neural networks, if parameter count information is not directly available,
    # try estimating the count as accurately as possible.
    # In case of ensemble approaches, add up parameters for all subsystems.
    total_parameters: 1800000
    MACS: 1.036 G
    # Approximate training time followed by the hardware used
    trainining_time: 3h (1 GTX 1080 Ti)
    # Model size in MB
    model_size: 14.281
  #Report here the energy consumption measured with e.g. codecarbon
  energy_consumption:
    training: 1.667
    test: 0.145
    #Energy consumption of the baseline (10 epochs) on your hardware
    baseline: 0.039
    
  #Report here the energy consumption measured with e.g. codecarbon
  energy_consumption:
    #Total energy
    energy_consumed:
      #Submission
      training: 1.180
      test: 0.119
      #Baseline
      baseline 10 epochs: 0.039
      baseline devtest: 0.119
    #GPU energy
    gpu_energy:
      #Submission
      training: 0.113
      test: 0.013
      #Baseline		
      baseline 10 epochs: 0.004
      baseline devtest: 0.0123

  # The training subsets used to train the model. Followed the amount of data (number of clips) used per subset.
  subsets: desed_weak (1578), desed_unlabel_in_domain (14412), desed_synthetic (30000), maestro_real (9592) 				# [desed_weak (xx), desed_unlabel_in_domain (xx), desed_synthetic (xx), maestro_real (xx), ...]

  #List here the external datasets you used for training
  external_datasets: AudioSet #AudioSet, ImageNet...

  #List here the pre-trained models you used
  pre_trained_models: BEATs  #BEATs, AST, PANNs...

  # URL to the source code of the system [optional, highly recommended]
  source_code: https://github.com/DCASE-REPO/DESED_task/tree/master/recipes/dcase2024_task4_baseline

# System results
results:
  devtest:
    # System result for development test datasets.
    desed:
      PSDS1: 0.491
    maestro:
      mPAUC: 0.695

Example meta information file for Task 5 baseline system task5/Morfi_QMUOL_task5_1/Morfi_QMUOL_task5_1.meta.yaml:

# Submission information
submission:
  # Submission label
  # Label is used to index submissions, to avoid overlapping codes among submissions
  # use the following way to form your label:
  # [Last name of corresponding author]_[Abbreviation of institute of the corresponding author]_task[task number]_[index number of your submission (1-4)]
  label: Morfi_QMUL_task5_1

  # Submission name
  # This name will be used in the results tables when space permits
  name: Cross-correlation baseline

  # Submission name abbreviated
  # This abbreviated name will be used in the results table when space is tight, maximum 10 characters
  abbreviation: xcorr_base

  # Submission authors in order, mark one of the authors as corresponding author.
  authors:
    # First author
    - lastname: Morfi
      firstname: Veronica
      email: g.v.morfi@qmul.ac.uk                     # Contact email address
      corresponding: true                             # Mark true for one of the authors

      # Affiliation information for the author
      affiliation:
        abbreviation: QMUL
        institute: Queen Mary University of London
        department: Centre for Digital Music
        location: London, UK

    # Second author
    - lastname: Stowell
      firstname: Dan
      email: dan.stowell@qmul.ac.uk                  # Contact email address

      # Affiliation information for the author
      affiliation:
        abbreviation: QMUL
        institute: Queen Mary University of London
        department: Centre for Digital Music
        location: London, UK

        #...


# System information
system:
  # SED system description, meta data provided here will be used to do
  # meta analysis of the submitted system. Use general level tags, if possible use the tags provided in comments.
  # If information field is not applicable to the system, use "!!null".
  description:

    # Audio input
    input_sampling_rate: any               # In kHz

    # Acoustic representation
    acoustic_features: spectrogram   # e.g one or multiple [MFCC, log-mel energies, spectrogram, CQT, PCEN, ...]

    # Data augmentation methods
    data_augmentation: !!null             # [time stretching, block mixing, pitch shifting, ...]

    # Embeddings
    # e.g. VGGish, OpenL3, ...
    embeddings: !!null

    # Machine learning
    # In case using ensemble methods, please specify all methods used (comma separated list).
    machine_learning_method: template matching         # e.g one or multiple [GMM, HMM, SVM, kNN, MLP, CNN, RNN, CRNN, NMF, random forest, ensemble, transformer, ...]
    # the system adaptation for "few shot" scenario.
    # For example, if machine_learning_method is "CNN", the few_shot_method might use one of [fine tuning, prototypical, MAML] in addition to the standard CNN architecture.
    few_shot_method: template matching         # e.g [fine tuning, prototypical, MAML, nearest neighbours...]

    # External data usage method
    # e.g. directly, embeddings, pre-trained model, ...
    external_data_usage: !!null

    # Ensemble method subsystem count
    # In case ensemble method is not used, mark !!null.
    ensemble_method_subsystem_count: !!null # [2, 3, 4, 5, ... ]

    # Decision making methods (for ensemble)
    decision_making: !!null                 # [majority vote, ...]

    # Post-processing, followed by the time span (in ms) in case of smoothing
    post-processing: peak picking, threshold				# [median filtering, time aggregation...]

  # System complexity, meta data provided here will be used to evaluate
  # submitted systems from the computational load perspective.
  complexity:

    # Total amount of parameters used in the acoustic model. For neural networks, this
    # information is usually given before training process in the network summary.
    # For other than neural networks, if parameter count information is not directly available,
    # try estimating the count as accurately as possible.
    # In case of ensemble approaches, add up parameters for all subsystems.
    total_parameters: !!null    # note that for simple template matching, the "parameters"==the pixel count of the templates, plus 1 for each param such as thresholding. 
    # Approximate training time followed by the hardware used
    trainining_time: !!null
    # Model size in MB
    model_size: !!null


  # URL to the source code of the system [optional, highly recommended]
  source_code:   

  # List of external datasets used in the submission.
  # A previous DCASE development dataset is used here only as example! List only external datasets
  external_datasets:
    # Dataset name
    - name: !!null
      # Dataset access url
      url: !!null
      # Total audio length in minutes
      total_audio_length: !!null            # minutes

# System results 
results:
  # Full results are not mandatory, but for through analysis of the challenge submissions recommended.
  # If you cannot provide all result details, also incomplete results can be reported.
  validation_set:
    overall:
      F-score: 2.01 # percentile

    # Per-dataset
    dataset_wise:
      HV:
        F-score: 1.22 #percentile
      PB:
        F-score: 5.84 #percentile

Example meta information file for Task 6 baseline system task6/Labbe_IRIT_task6_1/Labbe_IRIT_task6_1.meta.yaml:

# Submission information for task 6
submission:
  # Submission label
  # Label is used to index submissions.
  # Generate your label following way to avoid
  # overlapping codes among submissions
  # [Last name of corresponding author]_[Abbreviation of institute of the corresponding author]_task[task number]_[index number of your submission (1-4)]
  label: Labbe_IRIT_task6_1
  #
  # Submission name
  # This name will be used in the results tables when space permits
  name: DCASE2024 baseline system
  #
  # Submission name abbreviated
  # This abbreviated name will be used in the results table when space is tight.
  # Use maximum 10 characters.
  abbreviation: Baseline

# Authors of the submitted system. Mark authors in
# the order you want them to appear in submission lists.
# One of the authors has to be marked as corresponding author,
# this will be listed next to the submission in the results tables.
authors:
  # First author
  - lastname: Labbé
    firstname: Étienne
    email: etienne.labbe@irit.fr               # Contact email address
    corresponding: true                         # Mark true for one of the authors

    # Affiliation information for the author
    affiliation:
      abbreviation: IRIT
      institute: Institut de Recherche en Informatique de Toulouse
      department: Signaux et Images            # Optional
      location: Toulouse, France

  # Second author
  # ...

# System information
system:
  # System description, meta data provided here will be used to do
  # meta analysis of the submitted system.
  # Use general level tags, when possible use the tags provided in comments.
  # If information field is not applicable to the system, use "!!null".
  description:
    # Audio input / sampling rate
    # e.g., 16kHz, 22.05kHz, 44.1kHz, 48.0kHz
    input_sampling_rate: 32kHz

    # Acoustic representation
    # Here you should indicate what can or audio representation
    # you used. If your system used hand-crafted features (e.g.
    # mel band energies), then you can do
    #
    # `acoustic_features: mel energies`
    #
    # Else, if you used some pre-trained audio feature extractor, 
    # you can indicate the name of the system, for example
    #
    # `acoustic_features: cnn10`
    acoustic_features: ConvNeXt-Tiny
    # acoustic_features_url: 

    # Word embeddings
    # Here you can indicate how you treated word embeddings.
    # If your method learned its own word embeddings (i.e. you
    # did not used any pre-trained word embeddings) then you can
    # do
    #
    # `word_embeddings: learned`
    #  
    # Else, specify the pre-trained word embeddings that you used
    # (e.g., Word2Vec, BERT, etc).
    # If possible, please use the fullname of the model involved. (e.g., BART-base)
    word_embeddings: learned

    # Data augmentation methods
    # e.g., mixup, time stretching, block mixing, pitch shifting, ...
    data_augmentation: mixup + label smoothing

    # Method scheme
    # Here you should indicate the scheme of the method that you
    # used. For example
    machine_learning_method: encoder-decoder

    # Learning scheme
    # Here you should indicate the learning scheme. 
    # For example, you could specify either
    # supervised, self-supervised, or even 
    # reinforcement learning. 
    learning_scheme: supervised

    # Ensemble
    # - Here you should indicate the number of systems involved if you used ensembling.
    # - If you did not use ensembling, just write 1.
    ensemble_num_systems: 1

    # Audio modelling
    # Here you should indicate the type of system used for
    # audio modelling. For example, if you used some stacked CNNs, then
    # you could do
    #
    # audio_modelling: cnn
    #
    # If you used some pre-trained system for audio modelling,
    # then you should indicate the system used (e.g., COALA, COLA,
    # transformer).
    audio_modelling: !!null

    # Word modelling
    # Similarly, here you should indicate the type of system used
    # for word modelling. For example, if you used some RNNs,
    # then you could do
    #
    # word_modelling: rnn
    #
    # If you used some pre-trained system for word modelling, then you should indicate the system used (e.g., transformer).
    word_modelling: transformer

    # Loss function
    # - Here you should indicate the loss fuction that you employed.
    loss_function: cross_entropy

    # Optimizer
    # - Here you should indicate the name of the optimizer that you used. 
    optimizer: AdamW

    # Learning rate
    # - Here you should indicate the learning rate of the optimizer that you used.
    learning_rate: 5e-4

    # Weight decay
    # - Here you should indicate if you used any weight decay of your optimizer.
    # - Be careful because most optimizers uses a non-zero value by default.
    # - Use 0 for no weight decay.
    weight_decay: 2

    # Gradient clipping
    # - Here you should indicate if you used any gradient clipping. 
    # - Use 0 for no clipping.
    gradient_clipping: 1

    # Gradient norm
    # - Here you should indicate the norm of the gradient that you used for gradient clipping.
    # - Use !!null for no clipping.
    gradient_norm: "L2"

    # Metric monitored
    # - Here you should report the monitored metric for optimizing your method.
    # - For example, did you monitored the loss on the validation data (i.e. validation loss)?
    # - Or you monitored the SPIDEr metric? Maybe the training loss?
    metric_monitored: validation_loss

  # System complexity, meta data provided here will be used to evaluate
  # submitted systems from the computational load perspective.
  complexity:
    # About the amount of parameters used in the acoustic model.
    # - For neural networks, this information is usually given before training process in the network summary.
    # - For other than neural networks, if parameter count information is not directly available, try estimating the count as accurately as possible.
    # - In case embeddings are used, add up parameter count of the embedding extraction networks and classification network
    # - Use numerical value (do not use comma for thousands-separator).
    # - WARNING: In case of ensembling, add up parameters for all subsystems.

    # Learnable parameters
    learnable_parameters: 11914777
    # Frozen parameters (from the feature extractor and other parts of the model)
    frozen_parameters: 29388303
    # Total amount of parameters involved at inference time
    # Unless you used a complex method for prediction (e.g., re-ranking methods that use additional pretrained models), this value is equal to the sum of the learnable and frozen parameters.
    inference_parameters: 41303080

    # Training duration of your entire system in SECONDS.
    # - WARNING: In case of ensembling, add up durations for all subsystems trained.
    duration: 8840
    # Number of GPUs used for training
    gpu_count: 1
    # GPU model name
    gpu_model: NVIDIA GeForce RTX 2080 Ti

    # Optionally, number of multiply-accumulate operations (macs) to generate a caption
    # - You should use the same audio file ('Santa Motor.wav' from Clotho development-testing subset) for fair comparison with other models.
    # - You should include all the operations involved, including: feature extraction, beam search, etc. However, you can exclude operations used to resample the waveform.
    inference_macs: 48762319200

  # List of datasets used for training your system.
  # Unless you also used them to train your captioning system, you do not not need to include datasets involved to pretrain your encoder and/or decoder. (e.g., AudioSet for ConvNeXt in the baseline)
  # However, you should:
  # - Keep the Clotho development-training if you used it to train your system.
  # - Include here Clotho development-validation subset if you used it to train your system.
  # - Please always specify the correct subset of the dataset involved.
  train_datasets:
    - # Dataset name
      name: Clotho
      # Subset name (DCASE convention for Clotho)
      subset: development-training
      # Audio source (use !!null if not applicable)
      source: Freesound
      # Dataset access url
      url: https://doi.org/10.5281/zenodo.3490683
      # Has audio:
      has_audio: Yes
      # Has images
      has_images: No
      # Has video
      has_video: No
      # Has captions
      has_captions: Yes
      # Number of captions per audio
      nb_captions_per_audio: 5
      # Total amount of examples used
      total_audio_length: 3839
      # Used for (e.g., audio_modelling, word_modelling, audio_and_word_modelling)
      used_for: audio_and_word_modelling

  # List of datasets used for validation (checkpoint selection).
  # However, you should:
  # - Keep the Clotho development-validation if you used it to validate your system.
  # - If you did not used any validation dataset, just write `validation_datasets: []`.
  # - Please always specify the correct subset involved.
  validation_datasets:
    - # Dataset name
      name: Clotho
      # Subset name (DCASE convention for Clotho)
      subset: development-validation
      # Audio source (use !!null if not applicable)
      source: Freesound
      # Dataset access url
      url: https://doi.org/10.5281/zenodo.3490683
      # Has audio:
      has_audio: Yes
      # Has images
      has_images: No
      # Has video
      has_video: No
      # Has captions
      has_captions: Yes
      # Number of captions per audio
      nb_captions_per_audio: 5
      # Total amount of examples used
      total_audio_length: 1045

  # URL to the source code of the system (optional, write !!null if you do not want to share code)
  source_code: https://github.com/Labbeti/dcase2024-task6-baseline

# System results
results:
  development_testing:
    # System results on the development-testing split.
    # - Full results are not mandatory, however, they are highly recommended as they are needed for thorough analysis of the challenge submissions.
    # - If you are unable to provide all the results, incomplete results can also be reported.
    # - Each score should contain at least 3 decimals.
    meteor: 0.18979284501354263
    cider: 0.4619283292849137
    spice: 0.1335348395173806
    spider: 0.2977315844011471
    spider_fl: 0.2962828356306173
    fense: 0.5040896972480929
    vocabulary: 551.000

Example meta information file for Task 7 baseline system task7/Lee_GLI_task7_1/Lee_GLI_task7_1.meta.yaml:

# Submission information
submission:
  # Submission label
  # Label is used to index submissions.
  # Generate your label following way to avoid overlapping codes among submissions:
  # [Last name of corresponding author]_[Abbreviation of institute of the corresponding author]_task7_1(Index number of your submission. For task7, only 1 submission per team will be accepted.)
  label: Lee_GLI_task7_1

  # Submission name
  # This name will be used in the results tables when space permits.
  name: DCASE2024 baseline system

  # Submission name abbreviated
  # This abbreviated name will be used in the results table when space is tight.
  # Use a maximum of 10 characters.
  abbreviation: Baseline

  # Authors of the submitted system.
  # Mark authors in the order you want them to appear in submission lists.
  # One of the authors has to be marked as corresponding author, this will be listed next to the submission in the results tables.
  authors:
    # First author
    - firstname: Junwon
      lastname: Lee
      email: junwon.lee@gaudiolab.com

      # Affiliation information for the author
      affiliation:
        institution: Gaudio Lab, Inc./Korea Advanced Institute of Science & Technology (KAIST)
        department: AI Research/Music and Audio Computing Lab # Optional
        location: Seoul, Korea/Daejeon, Korea

    # Second author
    - firstname: Mathieu
      lastname: Lagrange
      email: mathieu.lagrange@ls2n.fr # Contact email address
      corresponding: true # Mark true for one of the authors

      # Affiliation information for the author
      affiliation:
        institution: CNRS, Ecole Centrale Nantes, Nantes Université
        department: LS2N # Optional
        location: Nantes, France

    # Third author
    - firstname: Modan
      lastname: Tailleur
      email: modan.tailleur@ls2n.fr

      # Affiliation information for the author
      affiliation:
        institution: CNRS, Ecole Centrale Nantes, Nantes Université
        department: Signal, IMage et Son (SIMS) # Optional
        location: Nantes, France

# System results
results:
  # Google Colab URL to generate sounds for evaluation [mandatory]
  # The sounds must be unique and must be generated by the code supplied in the colab.
  colab_url: https://colab.research.google.com/drive/1g5e89nnJBENteb-qASJxazgvuD2D_0EQ

  development_dataset:
    # System results for development dataset
    FAD: 61.2761

    # If you are unable to provide FAD for development dataset, also FAD results for other dataset than deverlopment dataset can be reported.
    # If information field is not applicable to the system, use "!!null".
    FAD_for_other_dataset: 61.2761 # Optional

    # Audio dataset used for calculating FAD
    evaluation_audio_datasets:
      # Dataset name
      - name: DCASE2024 Challenge Task 7 Development Dataset

        # Dataset access URL
        url: https://zenodo.org/records/10869644

        # Total audio length in minutes
        total_audio_length: 100

# System information
system:
  # System description, metadata provided here will be used to do a meta-analysis of the submitted system.
  # Use general level tags, when possible use the tags provided in comments.
  # If information field is not applicable to the system, use "!!null".
  description:
    # System input
    # Please specify all system input used (comma-separated list).
    input: text prompt

    # Machine learning methods
    # In case using ensemble methods, please specify all methods used (comma-separated list).
    # e.g. AE, VAE, GAN, Transformer, diffusion model, ensemble...
    machine_learning_method: VAE, CLAP, U-Net-based latent diffusion model
    phase_reconstruction: HiFi-GAN

    # Generated acoustic feature input to phase reconstructor
    # One or multiple labels, e.g. MFCC, log-mel energies, spectrogram, mel-spectrogram, CQT, ...
    acoustic_feature: mel-spectrogram

    # System training/processing pipeline stages
    # e.g. "contrastive language-audio pretraining", "encoding", "decoding", "phase reconstruction", ...
    pipeline: contrastive language-audio pretraining, encoding, decoding, phase reconstruction

    # Data augmentation methods
    # Please specify all methods used (comma-separated list).
    # e.g. mixup, time stretching, block mixing, pitch shifting, conditioning augmentation, ...
    data_augmentation: conditioning augmentation

    # Ensemble method subsystem count
    # In case ensemble method is not used, mark !!null.
    # e.g. 2, 3, 4, 5, ...
    ensemble_method_subsystem_count: !!null

  # System complexity
  complexity:
    # Total amount of parameters used in the acoustic model(s) and phase reconstruction method(s).
    # For neural networks, this information is usually given before training process in the network summary.
    # For other than neural networks, if parameter count information is not directly available, try estimating the count as accurately as possible.
    # In case of ensemble approaches, add up parameters for all subsystems.
    # In case embeddings are used, add up parameter count of the embedding extraction networks and phase reconstruction methods.
    # Use numerical value.
    total_parameters: 269992

  # List of ALL external audio datasets used in the submission. [mandatory]
  # Development dataset is used here only as an example, list only external datasets
  # If multiple external audio datasets are used, please copy the lines after [# Dataset name] and list information on all the audio datasets.
  # e.g. AudioSet, AudioCaps, Clotho, ...
  external_audio_datasets:
    # Dataset name
    - name: DCASE2024 Challenge Task 7 Development Dataset

      # Dataset access URL
      url: https://zenodo.org/records/10869644

      # Total audio length in minutes
      total_audio_length: 100

  # List of ALL external pre-trained models used in the submission.
  # If multiple external pre-trained models are used, please copy the lines after [# Model name] and list information on all the pre-trained models.
  # e.g. PANNs, VGGish, AST, BYOL-A, AudioLDM, ...
  external_models:
    # Model name
    - name: HiFi-GAN

      # Access URL for pre-trained model
      url: https://drive.google.com/drive/folders/1-eEYTB5Av9jNql0WGBlRoi-WH2J7bp5Y

      # How to use pre-trained model
      # e.g. encoder, decoder, weight quantization, vocoder, ... (comma-separated list)
      usage: vocoder

  # URL to the source code of the system [optional, highly recommended]
  # Reproducibility will be used to evaluate submitted systems.
  source_code: https://github.com/DCASE2024-Task7-Sound-Scene-Synthesis/AudioLDM-training-finetuning

# Questionnaire
questionnaire:
  # Do you agree to allow the DCASE distribution of 250 audio samples to evaluator(s) for the subjective evaluation? [mandatory]
  # The audio samples will not be distributed for any purpose other than subjective evaluation without other explicit permissions.
  distribute_audio_samples: Yes

  # Do you give permission for the task organizer to conduct a meta-analysis on 250 audio samples and to publish a technical report and paper using the results? [mandatory]
  # This does not mean that the copyright of audio samples is transferred to the DCASE community or task 7 organizers.
  publish_audio_samples: Yes

  # Do you agree to allow the DCASE use of 250 audio samples in a future version of this DCASE competition? (not required for competition entry, optional).
  # This may be used in future baseline comparisons or classification challenges related to this Foley challenge.
  # This does not mean that the copyright of audio samples is transferred to the DCASE community or task 7 organizers.
  use_audio_samples: Yes

Example meta information file for Task 8 baseline system task8/Xie_TAU_task8_1/Xie_TAU_task8_1.meta.yaml:

# Submission information for task 8
submission:
    # Submission label
    # Label is used to index submissions.
    # Generate your label following way to avoid overlapping codes among submissions:
    # [Last name of corresponding author]_[Abbreviation of institute of the corresponding author]_task[task number]_[index number of your submission (1-4)]
    label: Xie_TAU_task8_1
    #
    # Submission name
    # This name will be used in the results tables when space permits
    name: DCASE2024 baseline system
    #
    # Submission name abbreviated
    # This abbreviated name will be used in the result table when space is tight.
    # Use maximum 10 characters.
    abbreviation: Baseline

    # Authors of the submitted system.
    # Mark authors in the order you want them to appear in submission lists.
    # One of the authors has to be marked as corresponding author,
    # this will be listed next to the submission in the results tables.
    authors:
        # First author
        -   lastname: Xie
            firstname: Huang
            email: huang.xie@tuni.fi                    # Contact email address
            corresponding: true                         # Mark true for one of the authors

            # Affiliation information for the author
            affiliation:
                abbreviation: TAU
                institute: Tampere University
                department: Computing Sciences
                location: Tampere, Finland

        # Second author
        -   lastname: Virtanen
            firstname: Tuomas
            email: tuomas.virtanen@tuni.fi

            affiliation:
                abbreviation: TAU
                institute: Tampere University
                department: Computing Sciences
                location: Tampere, Finland

# System information
system:
    # System description, meta-data provided here will be used to do meta analysis of the submitted system.
    # Use general level tags, when possible use the tags provided in comments.
    # If information field is not applicable to the system, use "!!null".
    description:

        # Audio input / sampling rate, e.g. 16kHz, 22.05kHz, 44.1kHz, 48.0kHz
        input_sampling_rate: 44.1kHz

        # Acoustic representation
        # Here you should indicate what can or audio representation you used.
        # If your system used hand-crafted features (e.g. mel band energies), then you can do:
        #
        # `acoustic_features: mel energies`
        #
        # Else, if you used some pre-trained audio feature extractor, you can indicate the name of the system, for example:
        #
        # `acoustic_features: audioset`
        acoustic_features: log-mel energies

        # Text embeddings
        # Here you can indicate how you treated text embeddings.
        # If your method learned its own text embeddings (i.e. you did not use any pre-trained or fine-tuned NLP embeddings),
        # then you can do:
        #
        # `text_embeddings: learned`
        #
        # Else, specify the pre-trained or fine-tuned NLP embeddings that you used, for example:
        #
        # `text_embeddings: Sentece-BERT`
        text_embeddings: Sentece-BERT

        # Data augmentation methods for audio
        # e.g. mixup, time stretching, block mixing, pitch shifting, ...
        audio_augmentation: !!null

          # Data augmentation methods for text
        # e.g. random swapping, synonym replacement, ...
        text_augmentation: !!null

          # Learning scheme
          # Here you should indicate the learning scheme.
        # For example, you could specify either supervised, self-supervised, or even reinforcement learning.
        learning_scheme: self-supervised

        # Ensemble
        # Here you should indicate if you used ensemble of systems or not.
        ensemble: No

        # Audio modelling
        # Here you should indicate the type of system used for audio modelling.
        # For example, if you used some stacked CNNs, then you could do:
        #
        # audio_modelling: cnn
        #
        # If you used some pre-trained system for audio modelling, then you should indicate the system used,
        # for example, PANNs-CNN14, PANNs-ResNet38.
        audio_modelling: PANNs-CNN14

        # Text modelling
        # Similarly, here you should indicate the type of system used for text modelling.
        # For example, if you used some RNNs, then you could do:
        #
        # text_modelling: rnn
        #
        # If you used some pre-trained system for text modelling,
        # then you should indicate the system used (e.g. BERT).
        text_modelling: Sentece-BERT

        # Loss function
        # Here you should indicate the loss function that you employed.
        loss_function: InfoNCE

        # Optimizer
        # Here you should indicate the name of the optimizer that you used.
        optimizer: adam

        # Learning rate
        # Here you should indicate the learning rate of the optimizer that you used.
        learning_rate: 1e-3

        # Metric monitored
        # Here you should report the monitored metric for optimizing your method.
        # For example, did you monitor the loss on the validation data (i.e. validation loss)?
        # Or you monitored the training mAP?
        metric_monitored: validation_loss

    # System complexity, meta-data provided here will be used to evaluate
    # submitted systems from the computational load perspective.
    complexity:
        # Total amount of parameters used in the acoustic model.
        # For neural networks, this information is usually given before training process in the network summary.
        # For other than neural networks, if parameter count information is not directly
        # available, try estimating the count as accurately as possible.
        # In case of ensemble approaches, add up parameters for all subsystems.
        # In case embeddings are used, add up parameter count of the embedding
        # extraction networks and classification network
        # Use numerical value (do not use comma for thousands-separator).
        total_parameters: 732354

    # List of datasets used for the system (e.g., pre-training, fine-tuning, training).
    # Development-training data is used here only as example.
    training_datasets:
        -   name: Clotho-development
            purpose: training                           # Used for training system
            url: https://doi.org/10.5281/zenodo.4783391
            data_types: audio, caption                  # Contained data types, e.g., audio, caption, label.
            data_instances:
                audio: 3839                             # Number of contained audio instances
                caption: 19195                          # Number of contained caption instances
            data_volume:
                audio: 86353                            # Total amount durations (in seconds) of audio instances
                caption: 6453                           # Total word types in caption instances

        # More datasets
        #-   name:
        #    purpose: pre-training
        #    url:
        #    data_types: A, B, C
        #    data_instances:
        #        A: xxx
        #        B: xxx
        #        C: xxx
        #    data_volume:
        #        A: xxx
        #        B: xxx
        #        C: xxx

    # List of datasets used for validating the system, for example, optimizing hyperparameter.
    # Development-validation data is used here only as example.
    validation_datasets:
        -   name: Clotho-validation
            url: https://doi.org/10.5281/zenodo.4783391
            data_types: audio, caption
            data_instances:
                audio: 1045
                caption: 5225
            data_volume:
                audio: 23636
                caption: 2763

        # More datasets
        #-   name:
        #    url:
        #    data_types: A, B, C
        #    data_instances:
        #        A: xxx
        #        B: xxx
        #        C: xxx
        #    data_volume:
        #        A: xxx
        #        B: xxx
        #        C: xxx

    # URL to the source code of the system [optional]
    source_code: https://github.com/xieh97/dcase2023-audio-retrieval

# System results
results:
    development_testing:
        # System results for the development-testing split.
        # Full results are not mandatory, however, they are highly recommended as they are needed for through analysis of the challenge submissions.
        # If you are unable to provide all results, also incomplete results can be reported.
        R@1: 0.130
        R@5: 0.343
        R@10: 0.480
        mAP@10: 0.222

Example meta information file for Task 9 baseline system task9/Liu_Surrey_task9_1/Liu_Surrey_task9_1.meta.yaml:

# Submission information for task 9
submission:
  # Submission label
  # Label is used to index submissions.
  # Generate your label following way to avoid overlapping codes among submissions
  # [Last name of corresponding author]_[Abbreviation of institute of the corresponding author]_task[task number]_submission_[index number of your submission (1-4)]  
  label: Liu_Surrey_task9_1

  # Submission name
  # This name will be used in the results tables when space permits
  name: DCASE2024 baseline system

  # Submission name abbreviated
  # This abbreviated name will be used in the results table when space is tight.
  # Use maximum 10 characters.
  abbreviation: Baseline

# Authors of the submitted system. Mark authors in
# the order you want them to appear in submission lists.
# One of the authors has to be marked as corresponding author,
# this will be listed next to the submission in the results tables.
authors:
  # First author
  - lastname: Liu
    firstname: Xubo
    email: xubo.liu@surrey.ac.uk                # Contact email address
    corresponding: true                         # Mark true for one of the authors

    # Affiliation information for the author
    affiliation:
      abbreviation: Surrey
      institute: University of Surrey
      department: Centre for Vision, Speech and Signal Processing   # Optional
      location: Guilford, Surrey

  # Second author
  # ...

# System information
system:
  # System description, meta data provided here will be used to do
  # meta analysis of the submitted system.
  # Use general level tags, when possible use the tags provided in comments.
  # If information field is not applicable to the system, use "!!null".
  description:
    # Audio input sampling rate
    # e.g., 16kHz, 32kHz
    input_sampling_rate: 16kHz

    # Input Acoustic representation
    # Here you should indicate which audio representation you used as system input. 
    input_acoustic_features: waveform

    # Data augmentation methods
    # e.g., volume augmentation
    data_augmentation: volume augmentation

    # Method scheme
    # Here you should indicate the scheme of the method that you used. For example
    machine_learning_method: CLAP, ResUNet-based separation model, time-frequency masking

    # Ensemble
    # - Here you should indicate the number of systems involved if you used ensembling.
    # - If you did not use ensembling, just write 1.
    ensemble_num_systems: 1

    # Loss function
    # - Here you should indicate the loss fuction that you employed.
    loss_function: waveform l1 loss

    # List of ALL pre-trained models used in the submission.
    # If multiple pre-trained models are used, please copy the lines after [# Model name] and list information on all the pre-trained models.
    # e.g. CLAP, AudioSep ...
    - name: CLAP
      # Access URL for pre-trained model
      url: https://github.com/LAION-AI/CLAP

      # How to use pre-trained model
      # e.g. text encoder, separation model
      usage: text encoder
  
  # Training configurations
  train_config:
    # Optimizer
    # - Here you should indicate the name of the optimizer that you used. 
    optimizer: AdamW
    # Learning rate
    # - Here you should indicate the learning rate of the optimizer that you used.
    learning_rate: 1e-4
    # Weight decay
    # - Here you should indicate if you used any weight decay of your optimizer.
    # - Be careful because most optimizers uses a non-zero value by default.
    # - Use 0 for no weight decay.
    weight_decay: 2
    # Gradient clipping
    # - Here you should indicate if you used any gradient clipping. 
    # - Use 0 for no clipping.
    gradient_clipping: 1
    # Gradient norm
    # - Here you should indicate the norm of the gradient that you used for gradient clipping.
    # - Use !!null for no clipping.
    gradient_norm: "L2"
    # Training steps of your entire system.
    # - WARNING: In case of ensembling, add up steps for all subsystems trained.
    steps: 200000
    # Number of GPUs used for training
    gpu_count: 1
    # Total number of batch size used for training
    batch_size: 16
    # GPU model name
    gpu_model: NVIDIA A100

  # submitted systems from the computational load perspective.
  complexity:
    # Learnable parameters
    learnable_parameters: 26.45M
    # Total amount of parameters involved at inference time
    total_parameters: 238.60M 
  
  # List of datasets used for training your system.
  # Unless you also used them to train your LASS system, you do not need to include datasets involved to your pre-trained modules (e.g., datasets used to train CLAP models).
  # If the audio clips have caption annotations, you should specify their type (e.g., text labels, human-annotated caption, machine-generated caption).
  train_datasets:
    - # Dataset name
      name: LASS Task9 Development (Clotho)
      # Audio source (use !!null if not applicable)
      source: Freesound
      # Dataset access url
      url: https://doi.org/10.5281/zenodo.3490683
      # Is private
      is_private: No
      # Has audio:
      has_audio: Yes
      # Has images
      has_images: No
      # Has video
      has_video: No
      # Has captions
      has_captions: Yes
      # Captions type
      captions_type: human-annotated caption
      # Number of captions per audio
      nb_captions_per_audio: 5
      # Total amount of examples used
      total_audio_length: 6972
      # Total duration of audio clips (hours)
      total_duration: 37
      # Used for (e.g., lass_modelling)
      used_for: lass_modelling

    - # Dataset name
      name: LASS Task9 Development (FSD50K)
      # Audio source (use !!null if not applicable)
      source: Freesound
      # Dataset access url
      url: https://zenodo.org/record/4060432
      # Is private
      is_private: No
      # Has audio:
      has_audio: Yes
      # Has images
      has_images: No
      # Has video
      has_video: No
      # Has captions
      has_captions: Yes
      # Captions type
      captions_type: machine-generated caption
      # Number of captions per audio
      nb_captions_per_audio: 1
      # Total amount of examples used
      total_audio_length: 51197
      # Total duration of audio clips (hours)
      total_duration: 108
      # Used for (e.g., lass_modelling)
      used_for: lass_modelling

  # URL to the source code of the system (optional, write !!null if you do not want to share code)
  source_code: https://github.com/Audio-AGI/dcase2024_task9_baseline

# System results
results:
  validation_results:
    # System results on the validation (synth) split.
    # - Full results are not mandatory, however, they are highly recommended as they are needed for thorough analysis of the challenge submissions.
    # - If you are unable to provide all the results, incomplete results can also be reported.
    # - Each score should contain at least 3 decimals.
    SDR: 5.708
    SDRi: 5.673
    SISDR: 3.862

# Additional question
additional_question:
  # Does the submitted system need to be manually checked? For example, generative model-based approachs (e.g., diffusion model) 
  # usually perform not well in SDR-based metrics. In this case, organizers will randomly select a few separated audio files on 
  # which they will check algorithms that obtained lower SDR results with informal listening tests, 
  # and at their discretion will decide to include them in the subjective evaluation.
  need_manual_check: no
  detailed_reason: "null"

# Questionnaire
questionnaire:
  # Do you agree to allow the DCASE distribution of 200 separated audio samples in evaluation (real) to evaluator(s) for the subjective evaluation? [mandatory]
  # The audio samples will not be distributed for any purpose other than subjective evaluation without other explicit permissions.
  distribute_audio_samples: Yes

  # Do you give permission for the task organizer to conduct a meta-analysis on your submitted audio samples and to publish a technical report and paper using the results? [mandatory]
  # This does not mean that the copyright of audio samples is transferred to the DCASE community or task 9 organizers.
  publish_audio_samples: Yes

  # Do you agree to allow the DCASE use of your submitted separated audio samples in a future version of this DCASE competition? (not required for competition entry, optional).
  # This may be used in future baseline comparisons or separation challenges.
  # This does not mean that the copyright of audio samples is transferred to the DCASE community or task 9 organizers.
  use_audio_samples: Yes

Example meta information file for Task 10 baseline system task10/Bondi_BSCH_task10_1/Bondi_BSCH_task10_1.meta.yaml:

# Submission information
submission:
  # Submission label
  # Label is used to index submissions.
  # Generate your label following way to avoid
  # overlapping codes among submissions:
  # [Last name of corresponding author]_[Abbreviation of institute of the corresponding author]_task[task number]_[index number of your submission (1-4)]
  label: Bondi_BSCH_task10_1

  # Submission name
  # This name will be used in the results tables when space permits
  name: DCASE2024 baseline system

  # Submission name abbreviated
  # This abbreviated name will be used in the results table when space is tight.
  # Use maximum 10 characters.
  abbreviation: Baseline

  # Authors of the submitted system. Mark authors in
  # the order you want them to appear in submission lists.
  # One of the authors has to be marked as corresponding author,
  # this will be listed next to the submission in the results tables.
  authors:
    # First author
    - lastname: Bondi
      firstname: Luca
      email: Luca.Bondi@us.bosch.com                         # Contact email address
      corresponding: true                                    # Mark true for one of the authors
      # Affiliation information for the author
      affiliation:
        abbreviation: bsch
        institute: Bosch Research
        department: Human Machine Collaboration             # Optional
        location: USA

    # Second author
    - lastname: Ghaffarzadegan
      firstname: Shabnam
      email: Shabnam.Ghaffarzadegan@us.bosch.com   
      affiliation:
        abbreviation: bsch
        institute: Bosch Research
        department: Human Machine Collaboration             # Optional
        location: USA    

    # Third author
    - lastname: Lin
      firstname: Winston
      email: Winston.Lin@us.bosch.com
      affiliation:
        abbreviation: bsch
        institute: Bosch Research
        department: Human Machine Collaboration             # Optional
        location: USA  
 
# System information
system:
  # System description, meta data provided here will be used to do
  # meta analysis of the submitted system.
  # Use general level tags, when possible use the tags provided in comments.
  # If information field is not applicable to the system, use "!!null".
  description:

    # Audio input / sampling rate
    # e.g. 16kHz, 22.05kHz, 32kHz, 44.1kHz, 48.0kHz
    input_sampling_rate: 16kHz

    # Acoustic representation
    # one or multiple labels, e.g. MFCC, log-mel energies, spectrogram, CQT, raw waveform, ...
    acoustic_features: Generalized Cross-Correlation with Phase transform and Log Mel Spectrogram

    # Data augmentation methods
    # e.g. mixup, freq-mixstyle, dir augmentation, pitch shifting, time rolling, frequency masking, time masking, frequency warping, ...
    data_augmentation: !!null

    # Machine learning
    # e.g., (RF-regularized) CNN, RNN, CRNN, Transformer, ...
    machine_learning_method: CRNN

    # External data usage method
    # e.g. "dataset", "embeddings", "pre-trained model", ...
    external_data_usage: !!null

    # Method for handling the complexity restrictions
    # e.g. "knowledge distillation", "pruning", "precision_16", "weight quantization", "network design", ...
    complexity_management: !!null

    # System training/processing pipeline stages
    # e.g. "train teachers", "ensemble teachers", "train student using knowledge distillation", "quantization-aware training"
    pipeline: training

    # Machine learning framework
    # e.g. keras/tensorflow, pytorch, ...
    framework: pytorch

    # List all basic hyperparameters that were adapted for the different locations (or leave !!null in case no adaptations were made)
    # e.g. "lr", "epochs", "batch size", "weight decay", "freq-mixstyle probability", "frequency mask size", "time mask size", 
    #      "time rolling range", "dir augmentation probability", ...
    location_adaptations: !!null

    # List most important properties that make this system different from other submitted systems (or leave !!null if you submit only one system)
    # e.g. "architecture", "model size", "input resolution", "data augmentation techniques", "pre-training", "knowledge distillation", ...
    system_adaptations: !!null

  # System complexity
  complexity:
    # Total amount of parameters used in the acoustic model.
    # For neural networks, this information is usually given before training process
    # in the network summary.
    # For other than neural networks, if parameter count information is not directly
    # available, try estimating the count as accurately as possible.
    # In case of ensemble approaches, add up parameters for all subsystems.
    # In case embeddings are used, add up parameter count of the embedding
    # extraction networks and classification network
    # Use numerical value.
    total_parameters: 507396

  # List of external datasets used in the submission.
  external_datasets:
        #-   name:
        #    purpose: pre-training
        #    url:
        #    data_types: A, B, C
        #    data_instances:
        #        A: xxx
        #        B: xxx
        #        C: xxx
        #    data_volume:
        #        A: xxx
        #        B: xxx
        #        C: xxx

  # URL to the source code of the system [optional]
  source_code: https://github.com/boschresearch/acoustic-traffic-simulation-counting/

# System results
results:
  development_dataset:
    # System results on the development-test set for all provided locations.
    # Full results are not mandatory, however, they are highly recommended
    # as they are needed for through analysis of the challenge submissions.
    # If you are unable to provide all results, also incomplete
    # results can be reported.

    loc1:  # results on location 1
      car_left:
        Kendall's Tau Corr: 0.470
        RMSE: 2.449
      car_right:
        Kendall's Tau Corr: 0.478
        RMSE: 2.687
      cv_left:
        Kendall's Tau Corr: 0.231
        RMSE: 0.732
      cv_right:
        Kendall's Tau Corr: 0.189
        RMSE: 0.777

    loc2:  # results on location 2
      car_left:
        Kendall's Tau Corr: 0.446
        RMSE: 3.308
      car_right:
        Kendall's Tau Corr: 0.221
        RMSE: 3.560
      cv_left:
        Kendall's Tau Corr: 0.135
        RMSE: 0.468
      cv_right:
        Kendall's Tau Corr: -0.026
        RMSE: 0.610

    loc3:  # results on location 3
      car_left:
        Kendall's Tau Corr: 0.619
        RMSE: 1.629
      car_right:
        Kendall's Tau Corr: 0.593
        RMSE: 1.209
      cv_left:
        Kendall's Tau Corr: 0.102
        RMSE: 0.308
      cv_right:
        Kendall's Tau Corr: 0.272
        RMSE: 0.199

    loc4:  # results on location 4
      car_left:
        Kendall's Tau Corr: 0.456
        RMSE: 1.698
      car_right:
        Kendall's Tau Corr: 0.248
        RMSE: 2.210
      cv_left:
        Kendall's Tau Corr: 0
        RMSE: 0.548
      cv_right:
        Kendall's Tau Corr: 0.438
        RMSE: 0.728

    loc5:  # results on location 5
      car_left:
        Kendall's Tau Corr: 0.484
        RMSE: 0.662
      car_right:
        Kendall's Tau Corr: 0.575
        RMSE: 0.607
      cv_left:
        Kendall's Tau Corr: 0.092
        RMSE: 0.491
      cv_right:
        Kendall's Tau Corr: 0.108
        RMSE: 0.676

    loc6:  # results on location 6
      car_left:
        Kendall's Tau Corr: 0.825
        RMSE: 1.672
      car_right:
        Kendall's Tau Corr: 0.736
        RMSE: 1.950
      cv_left:
        Kendall's Tau Corr: 0.711
        RMSE: 0.535
      cv_right:
        Kendall's Tau Corr: 0.648
        RMSE: 0.441