Example meta information file for Task 1 baseline system task1/Font_UPF_task1_1/Font_UPF_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: Font_UPF_task1

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

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

  # 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: Font
      firstname: Frederic
      email: frederic.font@upf.edu           # Contact email address
      corresponding: true                    # Mark true for one of the authors
      # Affiliation information for the author
      affiliation:
        abbreviation: UPF
        institute: Universitat Pompeu Fabra (UPF)
        department: Music Technology Group (MTG)   # Optional
        location: Barcelona, Spain

    # Second author
    - lastname: Anastasopoulou
      firstname: Panagiota
      email: panagiota.anastasopoulou@upf.edu   
      affiliation:
        abbreviation: UPF
        institute: Universitat Pompeu Fabra (UPF)
        department: Music Technology Group (MTG)   # Optional
        location: Barcelona, Spain  

# 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 full source code of the system [optional]
  source_code: https://github.com/MTG/dcase2026_task1_baseline
  
  description:

    # Audio input / sampling rate
    # e.g. 16kHz, 22.05kHz, 32kHz, 44.1kHz, 48.0kHz
    input_sampling_rate: 48kHz

    # Audio representation (audio features or embedding spaces)
    # e.g. MFCC, log-mel energies, spectrogram, CQT, raw waveform, PANNs,
    # CLAP, EnCodec ...
    audio_representation: CLAP

    # Representation for text input (textual features, metadata items and/or
    # embedding spaces, only relevant in multimodal systems that use metadata
    # as input)
    # e.g. title, tags, description, Word2Vec, CLAP ...
    # Use !!null if the system does not use metadata as input (if the system is
    # audio-only).
    text_representation: title, tags, description, CLAP

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

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

    # External data usage method
    # e.g. dataset, embeddings, ...
    external_data_usage: embeddings

    # Method for considering taxonomy hierarchy in the system design
    # e.g. "loss function", "multiple classifiers", ...
    hierarchical_setting: !!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: 269992
    MACS: 1.036 G

  # List of external datasets used in the submission. If using embeddings from
  # pre-trained models, there's NO need to include the datasets used to train
  # the embedding models here.
  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 [OPTIONAL]
results:
  development_datasets:
    
    # System results for both development datasets 
    # If possible, please provide overall and class-wise results when
    # training/evaluating your systems on each of the development datasets
    # separately. You can follow the baseline code example to do that. Note that
    # development datasets do not include data splits, our baseline example uses
    # 5-fold cross-validation and reports the average performance across the 5
    # folds. You can reproduce the same experiment setup using the code
    # provided with the baseline system and using the same random seed to
    # generate the same folds.

    # Please refer to the baseline code for the calculation of the overall
    # metrics and class-wise (hP, hR, hF).
    # Set parameter lambda=0.75 (which is default in the baseline code).
    # Note that the numbers below are just examples, they do not correspond to
    # the actual performance of any system.
    
    bas10k-v1.2:
      overall:
        hp: 0.584
        hr: 0.688
        hf: 0.632

      class_wise:
        m-sp:    { hP:0.799, hR:0.875, hF:0.835}
        m-si:    { hP:0.794, hR:0.844, hF:0.818}
        m-m:     { hP:0.834, hR:0.944, hF:0.885}
        is-p:    { hP:0.799, hR:0.887, hF:0.841}
        is-s:    { hP:0.821, hR:0.887, hF:0.853}
        is-w:    { hP:0.790, hR:0.881, hF:0.833}
        is-k:    { hP:0.836, hR:0.900, hF:0.867}
        is-e:    { hP:0.753, hR:0.844, hF:0.796}
        sp-s:    { hP:0.790, hR:0.881, hF:0.833}
        sp-c:    { hP:0.821, hR:0.906, hF:0.862}
        sp-p:    { hP:0.764, hR:0.838, hF:0.799}
        fx-o:    { hP:0.788, hR:0.900, hF:0.841}
        fx-v:    { hP:0.788, hR:0.887, hF:0.835}
        fx-m:    { hP:0.802, hR:0.875, hF:0.837}
        fx-h:    { hP:0.778, hR:0.850, hF:0.812}
        fx-a:    { hP:0.795, hR:0.863, hF:0.828}
        fx-n:    { hP:0.805, hR:0.900, hF:0.850}
        fx-ex:	 { hP:0.797, hR:0.881, hF:0.837}
        fx-el:	 { hP:0.753, hR:0.825, hF:0.787}
        ss-n:    { hP:0.806, hR:0.887, hF:0.845}
        ss-i:    { hP:0.840, hR:0.900, hF:0.869}
        ss-u:    { hP:0.817, hR:0.887, hF:0.851}
        ss-s:    { hP:0.849, hR:0.925, hF:0.885}
      
    bsd35-cs:
      overall:
        hP: 0.339
        hR: 0.506
        hF: 0.406

      class_wise:
        m-sp:    { hP:0.594, hR:0.713, hF:0.648}
        m-si:    { hP:0.618, hR:0.725, hF:0.667}
        m-m:     { hP:0.566, hR:0.656, hF:0.608}
        is-p:    { hP:0.544, hR:0.650, hF:0.592}
        is-s:    { hP:0.579, hR:0.675, hF:0.623}
        is-w:    { hP:0.589, hR:0.700, hF:0.640}
        is-k:    { hP:0.576, hR:0.681, hF:0.625}
        is-e:    { hP:0.605, hR:0.700, hF:0.649}
        sp-s:    { hP:0.601, hR:0.688, hF:0.642}
        sp-c:    { hP:0.587, hR:0.706, hF:0.641}
        sp-p:    { hP:0.607, hR:0.719, hF:0.658}
        fx-o:    { hP:0.590, hR:0.694, hF:0.638}
        fx-v:    { hP:0.598, hR:0.719, hF:0.653}
        fx-m:    { hP:0.563, hR:0.644, hF:0.601}
        fx-h:    { hP:0.565, hR:0.669, hF:0.612}
        fx-a:    { hP:0.597, hR:0.688, hF:0.639}
        fx-n:    { hP:0.541, hR:0.631, hF:0.583}
        fx-ex:	 { hP:0.604, hR:0.719, hF:0.656}
        fx-el:	 { hP:0.587, hR:0.713, hF:0.644}
        ss-n:    { hP:0.561, hR:0.656, hF:0.605}
        ss-i:    { hP:0.598, hR:0.719, hF:0.653}
        ss-u:    { hP:0.573, hR:0.669, hF:0.617}
        ss-s:    { hP:0.583, hR:0.688, hF:0.631}

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: DCASE2026 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: 

      # Dataset access URL
      url: 

  # 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
    ToyCarEmu:
      auc_source: 69.62
      auc_target: 61.2
      pauc: 55.89

    ToyCar:
      auc_source: 75.62
      auc_target: 37.87
      pauc: 54.03

    bearingEmu:
      auc_source: 62.34
      auc_target: 59.56
      pauc: 59.85

    fan:
      auc_source: 61.45
      auc_target: 46.94
      pauc: 53.33

    gearboxEmu:
      auc_source: 68.23
      auc_target: 49.78
      pauc: 52.94

    sliderEmu:
      auc_source: 67.25
      auc_target: 45.05
      pauc: 50/38

    valveEmu:
      auc_source: 67.74
      auc_target: 68.78
      pauc: 55.08

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

TBA

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/He_CUHK_task5_1/He_CUHK_task5_1.meta.yaml:

# Submission information for task 5
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: He_CUHK_task5_1
  #
  # Submission name
  # This name will be used in the results tables when space permits
  name: Qwen3-Omni Baseline
  #
  # Submission name abbreviated
  # This abbreviated name will be used in the results table when space is tight.
  # Use maximum 10 characters.
  abbreviation: Qwen3base

# 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: He
    firstname: Haolin
    email: haolin.he@example.com                   # Contact email address
    corresponding: true                            # Mark true for one of the authors

    # Affiliation information for the author
    affiliation:
      abbreviation: CUHK
      institute: The Chinese University of Hong Kong
      department: Department of Computer Science      # Optional
      location: Hong Kong, China

  # 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: qwen3-omni  # 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: 30B # Number of total parameters of the system in billions.
  light_weighted: false # True if the system is lightweight submission (i.e. less than 30B parameters)

  # Post processing: Details about the post processing method used in the system
  post_processing: Direct string matching to extract the option letter from the model response

  # Optional. External data resources to train the system
  external_data_resources: [
    "AudioSet"
  ]

# System results on the development set.
    # - 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: 64.450%

Example meta information file for Task 6 baseline system task6/Munakata_LY_task6_1/Munakata_LY_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: Munakata_LY_task6_1
    #
    # Submission name
    # This name will be used in the results tables when space permits
    name: DCASE2026 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: Munakata
            firstname: Hokuto
            email: hokuto.munakata@lycorp.co.jp                    # Contact email address
            corresponding: true                         # Mark true for one of the authors

            # Affiliation information for the author
            affiliation:
                abbreviation: LY
                institute: LY Corporation
                department: Multimodal AI Unit
                location: Osaka, Japan

        # 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:
    model:
        # Describe the model architecture of your system.
        # If your system is an ensemble of multiple models, please describe all models used in the system.
        audio_models: [
          MS-CLAP,
        ]
        text_models: [
          MS-CLAP
        ]
        # If you use audio llms, such as Qwen2-audio, please specify the number of trainable and freezed parameters.
        LLMs: []
        # Describe the number of trainable parameters in your system.
        trainable_parameters: 7.1 M
        # Describe the number of freezed parameters in your system, if any.
        freezed_parameters: 158.4 M
        loss_function: [
          "L1",
          "gIoU",
          "cross_entropy"
        ]

    dataset:
        # If you use data augmentation, please specify the data augmentation methods used in your system.
        data_augmentation: !!null
        # If you use external data resources except for the provided dataset (i.e., CASTELLA and Clotho-Moment), please specify the name of the data resources used in your system.
        external_data_resources: [ 
            "audiocaps"
        ]
        # Describe the number of audio-caption pairs used for training your system.
        audio_captions: 48k

    ensemble: false

# System results
results:
    development_testing:
        # System results for the development-testing split.
        # Report Recall1@0.5 and Recall1@0.7 for the CASTELLA test set.
        # 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.
        Recall1@0.7: 0.0
        Recall1@0.5: 0.0

Example meta information file for Task 7 baseline system task7/Harju_TUNI_task7_1/Harju_TUNI_task7_1.meta.yaml:

TBA