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 in the 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: Schmid_CPJKU_task1_1

  # Submission name
  # This name will be used in the results tables when space permits
  name: DCASE2025 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: 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".
  
  # URL to the inference code of the system [required]
  inference_code: https://github.com/CPJKU/dcase2025_task1_inference
  
  # URL to the full source code (including training) of the system [optional]
  source_code: https://github.com/CPJKU/dcase2024_task1_baseline
  
  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 general student model with knowledge distillation",
    # "device-specific end-to-end fine-tuning", "quantization-aware training"
    pipeline: train general model, device-specific end-to-end fine-tuning 

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

    # How did you exploit available device information at inference time?
    # e.g., "per-device end-to-end fine-tuning", "device-specific adapters", "device-specific normalization", ...
    device_information: "per-device end-to-end fine-tuning"
    
    # Total number of models used at inference time
    # e.g., one general model and one model for each of A, B, C, S1, S2, S3 in baseline (= 7 models)
    num_models_at_inference: 7
    
    # Degree of parameter sharing between device-specific models
    # Options: "fully shared", "partially shared", "fully device-specific"
    model_weight_sharing: "fully device-specific"

  # System complexity
  # If complexity differs across device-specific models, report values for the most complex model.
  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 number of parameters in the most complex device-specific model
    # 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 torchinfo
    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

# System results
results:
  development_dataset:
    # Results on the development-test set for both the general model and the device-specific models.
    #
    # - The `general` block reports results when using a single model for all devices.
    # - The `device_specific` block reports results when using a dedicated model for each known device
    #   (e.g., A, B, C, S1–S6), and falling back to the general model for unknown devices.
    #
    # Providing both results allows for evaluating the benefit of device-specific adaptation.
    # Partial results are acceptable, but full reporting is highly encouraged for comparative analysis.
    
    device_specific:
    # Results using device-specific models for known devices,
    # and the general model for unknown devices.
    
      # Overall metrics
      overall:
        logloss: !!null   # Set to !!null if not computed
        accuracy: 51.89    # mean of class-wise accuracies

      # Class-wise metrics
      class_wise:
        airport:           { accuracy: 44.43, logloss: !!null }
        bus:               { accuracy: 64.81, logloss: !!null }
        metro:             { accuracy: 43.87, logloss: !!null }
        metro_station:     { accuracy: 48.22, logloss: !!null }
        park:              { accuracy: 72.75, logloss: !!null }
        public_square:     { accuracy: 32.04, logloss: !!null }
        shopping_mall:     { accuracy: 53.14, logloss: !!null }
        street_pedestrian: { accuracy: 34.43, logloss: !!null }
        street_traffic:    { accuracy: 74.10, logloss: !!null }
        tram:              { accuracy: 51.08, logloss: !!null }

      # Device-wise metrics
      device_wise:
        a:   { accuracy: 63.98, logloss: !!null }
        b:   { accuracy: 55.85, logloss: !!null }
        c:   { accuracy: 59.09, logloss: !!null }
        s1:  { accuracy: 48.68, logloss: !!null }
        s2:  { accuracy: 48.74, logloss: !!null }
        s3:  { accuracy: 52.72, logloss: !!null }
        s4:  { accuracy: 48.14, logloss: !!null }
        s5:  { accuracy: 47.23, logloss: !!null }
        s6:  { accuracy: 42.60, logloss: !!null }
    
    general: 
    # Results using the general model (used for unknown devices in section 'device-specific') for all devices
    
      # Overall metrics
      overall:
        logloss: !!null   # !!null, if you don't have the corresponding result
        accuracy: 50.72    # mean of class-wise accuracies

      # Class-wise metrics
      class_wise:
        airport:           { accuracy: 38.94, logloss: !!null }
        bus:               { accuracy: 62.28, logloss: !!null }
        metro:             { accuracy: 40.60, logloss: !!null }
        metro_station:     { accuracy: 50.72, logloss: !!null }
        park:              { accuracy: 72.03, logloss: !!null }
        public_square:     { accuracy: 29.20, logloss: !!null }
        shopping_mall:     { accuracy: 56.04, logloss: !!null }
        street_pedestrian: { accuracy: 34.76, logloss: !!null }
        street_traffic:    { accuracy: 73.21, logloss: !!null }
        tram:              { accuracy: 49.42, logloss: !!null }

      # Device-wise metrics
      device_wise:
        a:   { accuracy: 62.80, logloss: !!null }
        b:   { accuracy: 52.87, logloss: !!null }
        c:   { accuracy: 54.23, logloss: !!null }
        s1:  { accuracy: 48.52, logloss: !!null }
        s2:  { accuracy: 47.29, logloss: !!null }
        s3:  { accuracy: 52.86, logloss: !!null }
        s4:  { accuracy: 48.14, logloss: !!null }
        s5:  { accuracy: 47.23, logloss: !!null }
        s6:  { accuracy: 42.60, logloss: !!null }

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: DCASE2025 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
    MACS: 1.036 G
  
  # 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 2025 Challenge Task 2 Development Dataset

      # Dataset access URL
      url: https://zenodo.org/records/15097779

  # 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: 71.05
      auc_target: 53.52
      pauc: 49.7

    ToyTrain:
      auc_source: 61.76
      auc_target: 56.46
      pauc: 50.19

    bearing:
      auc_source: 66.53
      auc_target: 53.15
      pauc: 61.12

    fan:
      auc_source: 70.96
      auc_target: 38.75
      pauc: 49.46

    gearbox:
      auc_source: 64.8
      auc_target: 50.49
      pauc: 52.49

    slider:
      auc_source: 70.1
      auc_target: 48.77
      pauc: 52.32

    valve:
      auc_source: 63.53
      auc_target: 67.18
      pauc: 57.35

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: DCASE2025 Audio-only baseline

  # Submission name abbreviated
  # This abbreviated name will be used in the results table when space is tight, maximum 10 characters
  abbreviation: 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 AI
        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: Stereo                    # Stereo
    input_sampling_rate: 24kHz

    # Acoustic representation
    acoustic_features: log mel spectra      # e.g one or multiple [phase and magnitude spectra, log mel spectra, GCC-PHAT, TDOA, ...]
    # Video representation
    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: FSD50K, TAU-SRIR DB  # 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/DCASE2025_seld_baseline


# System results
results:

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

    # Overall score 
    overall:
      F_20_1: 22.8
      F_20_1_on: !!null
      DOAE: 24.5
      RDE: 0.41
      OSA: !!null

Example meta information file for Task 4 baseline system task4/Nguyen_NTT_task4_1/Nguyen_NTT_task4_1.meta.yaml:

# Submission information for task 4
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: Nguyen_NTT_task4_1

  # Submission name
  # This name will be used in the results tables when space permits
  name: DCASE2025 baseline system M2D ResUnetK

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

# 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: Nguyen
    firstname: BinhThien
    email: binhthien.nguyen@ntt.com             # Contact email address
    corresponding: true                         # Mark true for one of the authors

    # Affiliation information for the author
    affiliation:
      abbreviation: NTT
      institute: NTT Corporation
      department: Communication Science Laboratories   # Optional
      location: Atsugi, Kanagawa, Japan

  # 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: 32kHz

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

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

    # Method scheme
    # Here you should indicate the scheme of the method that you used. For example
    machine_learning_method: ResUNet-based separation model, M2D-based audio tagging model

    # 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: BCE, SDR 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. M2D ...
    - name: M2D
      # Access URL for pre-trained model
      url: https://github.com/nttcslab/m2d

      # How to use pre-trained model
      # e.g. text encoder, separation model
      usage: backbone for audio tagging model

  # submitted systems from the computational load perspective.
  complexity:
    # Total amount of parameters involved at inference time
    total_parameters: 115.40M
    # Number of GPUs used for training
    gpu_count: 8
    # GPU model name
    gpu_model: NVIDIA RTX 3090
  
  # List of datasets used for training your system.
  # Unless you also used them to train your system, you do not need to include datasets involved to your pre-trained modules (e.g., datasets used to train M2D models).
  train_datasets:
    - # Dataset name
      name: DCASE2025Task4Dataset
      # Audio source (use !!null if not applicable)
      source: DCASE2025Task4Dataset
      # Dataset access url
      url: https://zenodo.org/records/15117227
      # Is private
      is_private: No
      # Total duration of audio clips (hours)
      total_duration: !!null
      # Used for (e.g., s5_modelling)
      used_for: s5_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/nttcslab/dcase2025_task4_baseline

# System results
results:
  dev_set_test_result:
    # System results on the dev_set/test data.
    # - Each score should contain at least 3 decimals.
    CA-SDRi: 11.088
    label_prediction_accuracy: 59.800

# 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 5 baseline system task5/Kim_SNU_task5_1/Kim_SNU_task5_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: Kim_SNU_task5_1
  #
  # Submission name
  # This name will be used in the results tables when space permits
  name: Qwen2-Audio-7B Baseline
  #
  # Submission name abbreviated
  # This abbreviated name will be used in the results table when space is tight.
  # Use maximum 10 characters.
  abbreviation: Qwen2base

# 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: Kim
    firstname: Jaeyeon
    email: jaeyeonkim99@snu.ac.kr               # Contact email address
    corresponding: true                         # Mark true for one of the authors

    # Affiliation information for the author
    affiliation:
      abbreviation: SNU
      institute: Seoul National University
      department: Vision and Learning Lab          # Optional
      location: Seoul, Korea

  # Second author
  # ...

# System information
system:
  end_to_end: true # True if single end-to-end system, false if cascaded (chained) system
  pretrained: true # True if the system is pretrained, false if not
  pre_loaded: qwen2-audio-7b-instruct  # Name of the pre-trained model used in the system. If not pretrained, null
  autoregressive_model: true # True if the system is based on autoregressive language model, false if not
  model_size: 8.4B # Number of total parameters of the system in billions.
  light_weighted: false # True if the system is lightweight submission (i.e. less than 8B parameters)

  # Post processing: Details about the post processing method used in the system
  post_processing: Selected the option that has highest SentenceBERT similarity score with the model response

  # Optional. Extenral data resources to train the system
  external_data_resources: [ 
    "AudioSet",
    "AudioCaps"
  ]

# 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.
results:
  development:
    accuracy: 45.0%

Example meta information file for Task 6 baseline system task6/Primus_CPJKU_task6_1/Primus_CPJKU_task6_1.meta.yaml:

# Submission information for task 6
submission:
    # Submission label
    # The 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: Primus_CPJKU_task6_1
    #
    # Submission name
    # This name will be used in the results tables when space permits
    name: DCASE2025 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: Primus
            firstname: Paul
            email: paul.primus@jku.at                    # Contact email address
            corresponding: true                         # Mark true for one of the authors

            # Affiliation information for the author
            affiliation:
                abbreviation: CPJKU
                institute: Johannes Kepler University
                department: Institute of Computational Perception
                location: Linz, Austria

        # Second author
        -   lastname: Author
            firstname: Second
            email: first.last@some.org

            affiliation:
                abbreviation: ORG
                institute: Some Organization
                department: Department of Something
                location: City, Country

# 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/OptimusPrimus/

# System results
results:
    development_testing:
        # System results for the new and old development-testing split (with and without additional annotations).
        # Report R@1, R@5, R@10, and mAP@10 for the old version of Clotho-testing and mAP@16 for the new version of Clotho-testing.
        # 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: 0.0
        R@5: 0.0
        R@10: 0.0
        mAP@10: 0.0
        mAP@16: 0.0