Example meta information file for Task 6 baseline system task6/Gontier_INR_task6a_1/Gontier_INR_task6a_1.meta.yaml:

# Submission information for task 6, subtask A
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: gontier_inr_task6a_1
  #
  # Submission name
  # This name will be used in the results tables when space permits
  name: DCASE2022 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: Gontier
      firstname: Felix
      email: felix.gontier@inria.fr               # Contact email address
      corresponding: true                         # Mark true for one of the authors

      # Affiliation information for the author
      affiliation:
        abbreviation: INRIA
        institute: INRIA
        department: Multispeech            # Optional
        location: Nancy, 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: 16kHz

    # 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: VGGish

    # 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).
    word_embeddings: BART

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

    # 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 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 (e.g. COALA, COLA,
    # transfomer).
    audio_modelling: transformer

    # 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. transfomer).
    word_modelling: transformer

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

    # 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.
    leasrning_rate: 1e-5

    # Gradient clipping
    # Here you should indicate if you used any gradient clipping. 
    # You do this by indicating the value used for clipping. Use
    # 0 for no clipping.
    gradient_clipping: 0

    # Gradient norm
    # Here you should indicate the norm of the gradient that you
    # used for gradient clipping. This field is used only when 
    # gradient clipping has been employed.
    gradient_norm: !!null

    # 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:
    # 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: 140000000

  # List of external datasets used in the submission.
  # Development dataset is used here only as example, list only external datasets
  external_datasets:
    # Dataset name
    - name: Clotho

      # 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: 24430

      # Used for (e.g. audio_modelling, word_modelling, audio_and_word_modelling)
      used_for: audio_and_word_modelling

  # URL to the source code of the system [optional]
      source_code: https://github.com/audio-captioning/dcase-2021-baseline

# System results
results:
  development_evaluation:
    # System results for development evaluation 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.
    bleu1: 0.555
    bleu2: 0.358
    bleu3: 0.239
    bleu4: 0.156
    rougel: 0.364
    meteor: 0.164
    cider: 0.358
    spice: 0.109
    spider: 0.233

Example meta information file for Task 6 baseline system task6/Drossos_TAU_task6b_1/Xie_TAU_task6b_1.meta.yaml:

# Submission information for task 6 - subtask B
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_task6b_1
  #
  # Submission name
  # This name will be used in the results tables when space permits
  name: DCASE2022 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            # Optional
        location: Tampere, Finland

    # Second author
    - lastname: Lipping
      firstname: Samuel
      email: samuel.lipping@tuni.fi                # Contact email address

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

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

      # Affiliation information for the author
      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

    # Word embeddings
    # Here you can indicate how you treated word embeddings.
    # If your method learned its own word embeddings (i.e. you
    # did not use 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).
    word_embeddings: Word2Vec

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

    # Method scheme
    # Here you should indicate the scheme of the method that you
    # used. For example:
    machine_learning_method: cross-modal alignment

    # 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 (e.g. COALA, COLA,
    # transformer).
    audio_modelling: crnn

    # 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: word2vec

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

    # 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

    # Gradient clipping
    # Here you should indicate if you used any gradient clipping. 
    # You do this by indicating the value used for clipping. Use
    # 0 for no clipping.
    gradient_clipping: 0

    # Gradient norm
    # Here you should indicate the norm of the gradient that you
    # used for gradient clipping. This field is used only when 
    # gradient clipping has been employed.
    gradient_norm: !!null

    # 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:
    # 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 training the system.
  # Development-training data is used here only as example.
  training_datasets:
    - name: Clotho-development

      # Dataset access url
      url: https://doi.org/10.5281/zenodo.4783391

      # 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

      # Number of audio clips per caption
      nb_clips_per_caption: 1

      # Total amount durations (in seconds) of audio used
      total_audio_length: 86353

      # Total amount of captions used
      total_captions: 3839

  # 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

      # Dataset access url
      url: https://doi.org/10.5281/zenodo.4783391

      # 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

      # Number of audio clips per caption
      nb_clips_per_caption: 1

      # Total amount durations (in seconds) of audio used
      total_audio_length: 23636

      # Total amount of captions used
      total_captions: 1045

  # List of external datasets used in the submission.
  # Development dataset is used here only as example, list only external datasets
  external_datasets:
    # Dataset name
    - name: Clotho

      # Dataset access url
      url: https://doi.org/10.5281/zenodo.4783391

      # 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

      # Number of audio clips per caption
      nb_clips_per_caption: 1

      # Total amount durations (in seconds) of audio used
      total_audio_length: 133442

      # Total amount of captions used
      total_captions: 29645

      # Used for (e.g. audio_modelling, word_modelling, audio_and_word_modelling)
      used_for: audio_and_word_modelling

      # URL to the source code of the system [optional]
      source_code: https://github.com/xieh97/dcase2022-audio-retrieval

# System results
results:
  development_testing:
    # System results for 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: 0.03
    R@5: 0.11
    R@10: 0.19
    mAP@10: 0.07

Example meta information file for Task 7 baseline system task7/Choi_GLI_task7a_1/Choi_GLI_task7a_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_track[track]_[index number of your submission (1-4)]
  label: Choi_GLI_task7_trackA_1

  # Submission name
  # This name will be used in the results tables when space permits.
  name: DCASE2023 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
    - lastname: Keunwoo
      firstname: Choi
      email: keunwoo@gaudiolab.com # Contact email address
      corresponding: true # Mark true for one of the authors

      # Affiliation information for the author
      affiliation:
        institution: Gaudio Lab, Inc.
        department: AI Research # Optional
        location: Seoul, Korea

    # Second author
    - lastname: Jaekwon
      firstname: Im
      email: jaekwon@gaudiolab.com

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

    # Third author
    - lastname: Laurie
      firstname: Heller
      email: laurieheller@cmu.edu

      # Affiliation information for the author
      affiliation:
        institution: Carnegie Mellon University
        department: Psychology # Optional
        location: Pittsburgh, US

# 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/1FzbBf_FqWKu59i97ITibJbdPAqSzeMD4?usp=sharing

  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.
    # Average FAD
    average:
      FAD: 9.702

    # Class-wise FAD
    class_wise:
      DogBark:
        FAD: 13.411
      Footstep:
        FAD: 8.109
      GunShot:
        FAD: 7.951
      Keyboard:
        FAD: 5.230
      MovingMotorVehicle:
        FAD: 16.108
      Rain:
        FAD: 13.337
      Sneeze/Cough:
        FAD: 3.770

  # URL to the source code of the system [optional]
  source_code: https://github.com/DCASE2023-Task7-Foley-Sound-Synthesis/dcase2023_task7_baseline


# 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: sound event label

    # 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: VQ-VAE, PixelSNAIL
    phase_reconstruction: HiFi-GAN

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

    # System training/processing pipeline stages
    # e.g. "pretraining", "encoding" (from scratch), ,"weight quantization", "decoding", "phase reconstruction", ...
    pipeline: pretraining, encoding, weight quantization, decoding, phase reconstruction

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

  # 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. (only for track A)
  # 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, ESC-50, URBAN-SED, Clotho, ...
  external_audio_datasets:
    # Dataset name
    - name: DCASE2023 Challenge Task 7 Development Dataset

      # Dataset access URL
      url: https://drive.google.com/drive/folders/1GzfZvYVdbgDXnykOR93C3LCchPYBPh5I

      # Total audio length in minutes
      total_audio_length: 100

  # List of ALL external pre-trained models used in the submission. (only for track A)
  # 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, ...
  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/DCASE2023-Task7-Foley-Sound-Synthesis/dcase2023_task7_baseline

# Questionnaire
questionnaire:
  # Do you agree to allow the DCASE distribution of 700 audio samples (100 samples * 7 audio categories) 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 to publish 700 audio samples (100 samples * 7 audio categories) used in the evaluation on the challenge result page?
  # This is very important from the perspective of reproducible research, and we strongly encourage you to allow it.
  # 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 100 audio samples per category 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