2026 BioDCASE Task 2 : Development set

Calls description

BmA, BmB, and BmZ calls are specific to blue whales (Balaenoptera musculus intermedia, Bm), while Bp20 and Bp20Plus calls are characteristic of fin whales (Balaenoptera physalus quoyi, Bp). Both species also produce downsweeps.

As described by Miller et al. (see "Related Works"), BmA calls consist of a constant-frequency tone between 25 and 28 Hz, without additional units. BmB calls are similar but followed by a partial or full inter-tone downsweep. BmZ calls contain two tonal units: A (higher frequency) and C (lower frequency). Occasionally, a B downsweep unit appears between them, forming a "Z" shape on spectrograms.

Bp20 and Bp20Plus vocalizations are pulsed calls with peak energy at 20 Hz (Bp20) and additional energy at higher frequencies (80–100 Hz) in Bp20Plus.

Downsweeps are characterized by a continuous frequency modulation from f₁ to f₂, where f₁ > f₂. Example spectrograms are available on the here, with more detailed references in Miller et al.

Dataset statistics

Train set

Validation set

A more complete version of this table is available here, with more statistics within the different classes and more information on the recording deployments.

Supplementary resources

• All datasets, annotations and pre-trained models from this list are allowed. In particular, we inform participants that additional unlabeled data originating from the same scientific program are available here, and that other comparable datasets from the same geographical regions can be accessed on the OPUS platform ;
• Use of other external data (e.g. audio files, annotations) and pre-trained models are allowed only after approval from the task coordinators (contact: dorian.cazau@ensta.fr). Note that these external data and models should be at least publicly available.

Evaluation set

The evaluation set for this task will be released on June 1, 2026. 

Data collection 

Original data were collected, curated, annotated and published by Miller, B.S., The IWC-SORP/SOOS Acoustic Trends Working Group., Balcazar, N. et al. An open access dataset for developing automated detectors of Antarctic baleen whale sounds and performance evaluation of two commonly used detectors. Sci Rep 11, 806 (2021). https://doi.org/10.1038/s41598-020-78995-8 (see Related works section)

Dataset version control

Below we track changes applied to our challenge datasets over time.

Original data 

They can be accessed via the Australian Antarctic Data Centre at https://data.aad.gov.au/metadata/records/AcousticTrends_BlueFinLibrary

BioDCASE2025 

Minor changes were brought to the original data to fit the challenge formatting conventions : 

• adopting more consistent naming conventions, particularly for file paths. All .wav filenames now follow the format "YYYY-mm-ddTHH-MM-SS_fff.wv", and the same convention is used in the CSV files under the "filename" column. Additionally, the start and end timestamps for temporal annotation boxes are formatted as "YYYY-mm-ddTHH:MM:SS.ffffff+zz:zz", all in Zulu Time,

• pooling together call-type-specific Raven tables into one CSV file per subdataset, named after the site-year annotated,
• resampling all audio files at 250 Hz, the minimal original sample rate of several subdatasets. This was done to standardize sample rates and because the vocalizations of interest are very low-frequency calls (15–120 Hz), ensuring no loss of information at  sampling rate of 250 Hz

BioDCASE2026

During the 2025 edition, several minor bugs were identified and reported here. The following fixes have been applied for the 2026 version :

• Wrong file names : 5 annotations in the dataset elephantisland2014 had the wrong filename "2014-10-05T02-00-00_000.wav", it was replaced with the correct one "2014-10-05T03-00-00_000.wav" ;
• Truncated annotation boxes at the end of audio files : some annotation boxes exceeded their audio files, either because the annotator pulled the Raven box a bit too long or because a longer audio file was used during annotation. The fixes applied were : 1) the end timestamp of a truncated annotation box is set to the audio file duration , 2) if the resulting truncated box is shorter than 0.286 seconds (corresponding to the smallest annotation durations from BmABZ, downsweeps and Bp20 labels), then it is removed from the annotation set. 76 annotation boxes were reduced in time and only 2 were removed.

Changes in datasets between the 2025 and 2026 editions can be further inspected throug the summary statistics tables (2025 and 2026).

Open access

Data used in this study are publicly available under a Creative Commons 4.0 Attribution licence. It is attributed to Miller, B.S., The IWC-SORP/SOOS Acoustic Trends Working Group., Balcazar, N. et al.

Contact info 

Please, send any feedback or question to : 

Dorian CAZAU (dorian.cazau@ensta.fr) | Lucie JEAN-LABADYE (lucie.jean-labadye@sorbonne-universite.fr) | Cléa PARCERISAS (clea.parcerisas@vliz.be)