Example meta information file for Task 1 baseline system task1/Martin_TAU_task1a_1/Martin_TAU_task1a_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: Martin_TAU_task1a_1
 # Submission name
 # This name will be used in the results tables when space permits
 name: DCASE2021 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: Martín Morató
 firstname: Irene
 email: irene.martinmorato@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: Heittola
 firstname: Toni
 email: toni.heittola@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: Mesaros
 firstname: Annamaria
 email: annamaria.mesaros@tuni.fi
 # Affiliation information for the author
 affiliation:
 abbreviation: TAU
 institute: Tampere University
 department: Computing Sciences
 location: Tampere, Finland
 # Fourth 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
 # one or multiple labels, e.g. MFCC, log-mel energies, spectrogram, CQT, raw waveform, ...
 acoustic_features: log-mel energies
 # Embeddings
 # e.g. VGGish, OpenL3, ...
 embeddings: !!null
 # Data augmentation methods
 # e.g. mixup, time stretching, block mixing, pitch shifting, ...
 data_augmentation: !!null
 # Machine learning
 # In case using ensemble methods, please specify all methods used (comma separated list).
 # one or multiple, e.g. GMM, HMM, SVM, MLP, CNN, RNN, CRNN, ResNet, ensemble, ...
 machine_learning_method: CNN
 # 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 methods
 # e.g. average, majority vote, maximum likelihood, ...
 decision_making: !!null
 # External data usage method
 # e.g. directly, embeddings, pre-trained model, ...
 external_data_usage: embeddings
 # Method for handling the complexity restrictions
 # e.g. weight quantization, sparsity, ...
 complexity_management: weight quantization
 # 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: 46246
 # Total amount of non-zero parameters in the acoustic model.
 # Calculated with same principles as "total_parameters".
 # Use numerical value (do not use comma for thousands-separator).
 total_parameters_non_zero: 46246
 # Model size calculated as instructed in task description page.
 # Use numerical value, unit is KB
 model_size: 90.3 # KB
 # 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: TAU Urban Acoustic Scenes 2020 Mobile, Development dataset
 # Dataset access url
 url: https://doi.org/10.5281/zenodo.3819968
 # Total audio length in minutes
 total_audio_length: 3840 # minutes
 # URL to the source code of the system [optional]
 source_code: https://github.com/marmoi/dcase2021_task1a_baseline
# System results
results:
 development_dataset:
 # System results for development dataset with provided the cross-validation setup.
 # 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.
 # Overall metrics
 overall:
 logloss: 1.461
 accuracy: 46.9 # mean of class-wise accuracies
 # Class-wise metrics
 class_wise:
 airport:
 logloss: 1.497
 accuracy: 31.1
 bus:
 logloss: 1.475
 accuracy: 40.1
 metro:
 logloss: 1.457
 accuracy: 48.1
 metro_station:
 logloss: 2.060
 accuracy: 29.6
 park:
 logloss: 1.217
 accuracy: 63.6
 public_square:
 logloss: 1.738
 accuracy: 36.0
 shopping_mall:
 logloss: 1.136
 accuracy: 61.3
 street_pedestrian:
 logloss: 1.522
 accuracy: 47.1
 street_traffic:
 logloss: 1.145
 accuracy: 68.0
 tram:
 logloss: 1.360
 accuracy: 44.3
 # Device-wise
 device_wise:
 a:
 logloss: !!null
 accuracy: 63.9
 b:
 logloss: !!null
 accuracy: 52.2
 c:
 logloss: !!null
 accuracy: 56.3
 s1:
 logloss: !!null
 accuracy: 44.2
 s2:
 logloss: !!null
 accuracy: 43.9
 s3:
 logloss: !!null
 accuracy: 44.5
 s4:
 logloss: !!null
 accuracy: 38.5
 s5:
 logloss: !!null
 accuracy: 40.6
 s6:
 logloss: !!null
 accuracy: 38.2

Example meta information file for Task 1 baseline system task1/Wang_TAU_task1b_1/Wang_TAU_task1b_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: Wang_TAU_task1b_1
 # Submission name
 # This name will be used in the results tables when space permits
 name: DCASE2021 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: Wang
 firstname: Shanshan
 email: shanshan.wang@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: Heittola
 firstname: Toni
 email: toni.heittola@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: Mesaros
 firstname: Annamaria
 email: annamaria.mesaros@tuni.fi
 # Affiliation information for the author
 affiliation:
 abbreviation: TAU
 institute: Tampere University
 department: Computing Sciences
 location: Tampere, Finland
 # Fourth 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 / channels
 # one or multiple: e.g. mono, binaural, left, right, mixed, ...
 input_channels: mono
 # Audio input / sampling rate
 # e.g. 16kHz, 22.05kHz, 44.1kHz, 48.0kHz
 input_sampling_rate: 48.0kHz
 # Acoustic representation
 # one or multiple labels, e.g. MFCC, log-mel energies, spectrogram, CQT, raw waveform, ...
 acoustic_features: log-mel energies
 # Embeddings
 # e.g. VGGish, OpenL3, ...
 audio_embeddings: OpenL3
 visual_embeddings: OpenL3
 # Data augmentation methods
 # e.g. mixup, time stretching, block mixing, pitch shifting, ...
 data_augmentation: !!null
 # Machine learning
 # In case using ensemble methods, please specify all methods used (comma separated list).
 # one or multiple, e.g. GMM, HMM, SVM, MLP, CNN, RNN, CRNN, ResNet, ensemble, ...
 machine_learning_method: CNN
 # Ensemble method subsystem count
 # In case ensemble method is not used, mark !!null.
 # e.g. 2, 3, 4, 5, ...
 ensemble_method_subsystem_count: !!null
 # How information from modalities are combined
 # e.g. audio only, video only, early fusion, late fusion
 modality_combination: early fusion
 # Decision making methods
 # e.g. average, majority vote, maximum likelihood, ...
 decision_making: maximum likelihood
 # External data usage method
 # e.g. directly, embeddings, pre-trained model, ...
 external_data_usage: embeddings
 # 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 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: 14553134
 # total parameter is 14553134
 # audio-visual model parameter is 34,186
 # audio model parameters: 338634
 # video model parameters: 338634
 # audio embedding extraction from OpenL3 9150660
 # video embedding extraction from OpenL3 4691020
 # Amount of parameters used in the acoustic model. Indicated the same way than total_parameters.
 # Use numerical value (do not use comma for thousands-separator).
 total_parameters_audio: 9489294
 # Amount of parameters used in the visual model. Indicated the same way than total_parameters
 # Use numerical value (do not use comma for thousands-separator).
 total_parameters_visual: 5029654
 # 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: TAU Urban Audio-Visual Scenes 2021, Development dataset
 # Dataset access url
 url: https://zenodo.org/record/4477542#.YK3yipMza3A
 # Total audio length in minutes
 total_audio_length: 2040 # minutes
 # URL to the source code of the system [optional]
 source_code: https://github.com/shanwangshan/TAU-urban-audio-visual-scenes
# System results
results:
 development_dataset:
 # System results for development dataset with provided the cross-validation setup.
 # 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.
 # Overall metrics
 overall:
 logloss: 0.658
 accuracy: 77.0 # mean of class-wise accuracies
 # Class-wise metrics
 class_wise:
 airport:
 logloss: 0.963
 accuracy: 66.8
 bus:
 logloss: 0.396
 accuracy: 85.9
 metro:
 logloss: 0.541
 accuracy: 80.4
 metro_station:
 logloss: 0.565
 accuracy: 80.8
 park:
 logloss: 0.710
 accuracy: 77.2
 public_square:
 logloss: 0.732
 accuracy: 71.1
 shopping_mall:
 logloss: 0.839
 accuracy: 72.6
 street_pedestrian:
 logloss: 0.877
 accuracy: 72.7
 street_traffic:
 logloss: 0.296
 accuracy: 89.6
 tram:
 logloss: 0.659
 accuracy: 73.1

Example meta information file for Task 2 baseline system task2/Kawaguchi_HIT_task2_1/Kawaguchi_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: Kawaguchi_HIT_task2_1
 # Submission name
 # This name will be used in the results tables when space permits.
 name: DCASE2021 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: Kawaguchi
 firstname: Yohei
 email: yohei.kawaguchi.xk@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
 - lastname: Imoto
 firstname: Keisuke
 email: keisuke.imoto@ieee.org
 # Affiliation information for the author
 affiliation:
 institution: Doshisha University
 location: Kyoto, Japan
 # Third author
 - lastname: Koizumi
 firstname: Yuma
 email: koizumi.yuma@ieee.org
 # Affiliation information for the author
 affiliation:
 institution: Google LLC
 location: Tokyo, 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 adaptation
 # Please specify all methods used (comma-separated list).
 # e.g. fine-tuning, AdaFlow, ...
 domain_adaptation_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
 # 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 2021 Challenge Task 2 Development Dataset
 # Dataset access URL
 url: https://zenodo.org/record/4562016
 # URL to the source code of the system [optional, highly recommended]
 # Reproducibility will be used to evaluate submitted systems.
 source_code: https://github.com/y-kawagu/dcase2021_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.
 # Harmonic mean of AUCs over all sections (00, 01, and 02) and domains [%]
 # No need to round numbers
 ToyCar:
 harmonic_mean_auc: 62.49
 harmonic_mean_pauc: 52.36
 ToyConveyor:
 harmonic_mean_auc: 61.71
 harmonic_mean_pauc: 53.81
 fan:
 harmonic_mean_auc: 63.24
 harmonic_mean_pauc: 53.38
 gearbox:
 harmonic_mean_auc: 65.97
 harmonic_mean_pauc: 52.76
 pump:
 harmonic_mean_auc: 61.92
 harmonic_mean_pauc: 54.41
 slider:
 harmonic_mean_auc: 66.74
 harmonic_mean_pauc: 55.94
 valve:
 harmonic_mean_auc: 53.41
 harmonic_mean_pauc: 50.54

Example meta information file for Task 3 baseline system task3/Politis_TAU_task3_1/Politis_TAU_task3_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_task3_1
 # Submission name
 # This name will be used in the results tables when space permits
 name: DCASE2021 Ambisonic example
 # Submission name abbreviated
 # This abbreviated name will be used in the results table when space is tight, maximum 10 characters
 abbreviation: FOA_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: Adavanne
 firstname: Sharath
 email: sharath.adavanne@tuni.fi # Contact email address
 # Affiliation information for the author
 affiliation:
 abbreviation: TAU
 institute: Tampere University
 department: Audio Research Group
 location: Tampere, Finland
 # Third author
 - lastname: Virtanen
 firstname: Tuomas
 email: tuomas.virtanen@tuni.fi # Contact email address
 # Affiliation information for the author
 affiliation:
 abbreviation: TAU
 institute: Tampere University
 department: Audio Research Group
 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, if possible use the tags provided in comments.
 # If information field is not applicable to the system, use "!!null".
 description:
 # Audio input
 input_format: Ambisonic 	# e.g. 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 ...]
 # 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, ...]
 # 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: 116118
 # URL to the source code of the system [optional]
 source_code: https://github.com/sharathadavanne/seld-dcase2021
# Evaluation setup used for training your final submitted model
evaluation_setup:
 # List the folds used for training and validating your submitted evaluation model. For instance the baseline SELDnet was trained and validated with the following folds from the dataset
 training_folds: 2, 3, 4, 5, 6
 validation_folds: 1
# System results
results:
 development_dataset:
 # System result for development dataset with the provided evaluation setup.
 # Overall score 
 overall:
 ER_20: 0.69
 F_20: 33.9
 LE_CD: 24.1
 LR_CD: 43.9

Example meta information file for Task 4 baseline system task4/Turpault_INR_task4_SED_1/Turpault_INR_task4_SED_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: Turpault_INR_task4_SED_1
 # Submission name
 # This name will be used in the results tables when space permits
 name: DCASE2020 SED baseline system
 # Submission name abbreviated
 # This abbreviated name will be used in the results table when space is tight, maximum 10 characters
 abbreviation: SED Baseline
 # Submission authors in order, mark one of the authors as corresponding author.
 authors:
 # First author
 - lastname: Turpault
 firstname: Nicolas
 email: nicolas.turpault@inria.fr # Contact email address
 corresponding: true # Mark true for one of the authors
 # Affiliation information for the author
 affiliation:
 abbreviation: INR
 institute: Inria Nancy Grand-Est
 department: Department of Natural Language Processing & Knowledge Discovery
 location: Nancy, France
 # Second author
 - lastname: Serizel
 firstname: Romain
 email: romain.serizel@loria.fr # Contact email address
 # Affiliation information for the author
 affiliation:
 abbreviation: ULO
 institute: University of Lorraine, Loria
 department: Department of Natural Language Processing & Knowledge Discovery
 location: Nancy, France
 # Third author
 - firstname: John
 lastname: Hershey
 # Affiliation information for the author
 affiliation:
 abbreviation: GOO
 institue: Google, Inc.
 department: AI Perception
 Location: Cambridge, United States
 # Fourth author
 - firstname: Scott
 lastname: Wisdom
 # Affiliation information for the author
 affiliation:
 abbreviation: GOO
 institue: Google, Inc.
 department: AI Perception
 Location: Cambridge, United States
 # Fifth author
 - firstname: Hakan
 lastname: Erdogan
 # Affiliation information for the author
 affiliation:
 abbreviation: GOO
 institue: Google, Inc.
 department: AI Perception
 Location: Cambridge, 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, followed by the time span (in ms) in case of smoothing
 post-processing: median filtering (93ms)				# [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: 1112420
 # Approximate training time followed by the hardware used
 trainining_time: 3h (1 GTX 1080 Ti)
 # Model size in MB
 model_size: 4.5
 # The training subsets used to train the model. Followed the amount of data (number of clips) used per subset.
 subsets: 				# [weak (xx), unlabel_in_domain (xx), synthetic (xx), FUSS (xx)...]
 # URL to the source code of the system [optional, highly recommended]
 source_code: https://github.com/turpaultn/dcase20_task4/tree/public_branch/baseline
# System results
results:
 # Full results are not mandatory, but for through analysis of the challenge submissions recommended.
 # If you cannot provide all results, also incomplete results can be reported.
 development_dataset:
 # System result for development dataset with provided the cross-validation setup.
 overall:
 PSDS1: 0.420
 PSDS2: 0.610

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: Nolasco_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: Nolasco
 firstname: Ines
 email: i.dealmeidanolasco@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/Drossos_TAU_task6_1/Drossos_TAU_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: drossos_tau_task6_1
 #
 # Submission name
 # This name will be used in the results tables when space permits
 name: DCASE2021 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: Drossos
 firstname: Konstantinos
 email: konstantinos.drossos@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 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: one-hot
 # 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: cnn
 # 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: rnn
 # 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: adam
 # Learning rate
 # Here you should indicate the learning rate of the optimizer
 # that you used.
 leasrning_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: 46246
 # 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: 0.378
 bleu2: 0.119
 bleu3: 0.050
 bleu4: 0.017
 rougel: 0.263
 meteor: 0.078
 cider: 0.075
 spice: 0.028
 spider: 0.051