{"url":"/dataset/biosed-acpd","name":"BIOSED-ACPD","full_name":null,"description_markdown":"BIOSED-ACPD: BIOacoustic Sound Event Detection - Adaptive Change Point Detection dataset\r\n\r\nDescription.\r\nThis dataset contains the generated audio mixtures with strong annotations, and pre-computed BirdNET embeddings used in the paper \"From Weak to Strong Sound Event Labels using Adaptive Change-Point Detection and Active Learning\". The results of the paper can be reproduced at three different levels using this dataset:\r\n\r\nresults_eusipco_2024.zip : contains the experiment results used to produce all tables and figures in the paper.\r\ndata.zip : contains the pre-computed BirdNET embeddings, labels and the JAMS files from Scaper.\r\naudio_data.tar.gz : contains the pre-generated audio mixtures for the datasets.\r\nAt level (1) the figures and tables are produced using the exact results from the experiments presented in the paper, at level (2) the pre-computed embeddings and annotations are used to run the experiments and reproduce the results, and at level (3) the embeddings can be computed using BirdNET on the audio mixtures. For the audio mixtures download all parts and run \"cat audio_data.tar.gz.* > audio_data.tar.gz\".\r\n\r\nsource code : https://github.com/johnmartinsson/adaptive-change-point-detection/blob/main/README.md\r\npaper link     : https://arxiv.org/abs/2403.08525\r\n\r\nCite as.\r\n\r\n@misc{martinsson2024weak,\r\n      title={From Weak to Strong Sound Event Labels using Adaptive Change-Point Detection and Active Learning}, \r\n      author={John Martinsson and Olof Mogren and Maria Sandsten and Tuomas Virtanen},\r\n      year={2024},\r\n      eprint={2403.08525},\r\n      archivePrefix={arXiv},\r\n      primaryClass={cs.SD}\r\n}\r\n\r\n\r\nAttribution.\r\nThe audio mixtures are derived from three openly available audio datasets:\r\n\r\nNolasco, I., Singh, S., Strandburg-Peshkin, A., Gill, L., Pamula, H., Grout, E., Morford, J., Emmerson, M., Jensens, F., Whitehead, H., Kiskin, I., Vidana-Vila, E., Lostanlen, V., & Stowell, D. (2022). DCASE 2022 Task 5: Few-shot Bioacoustic Event Detection Evaluation Set [Data set]. Zenodo. https://doi.org/10.5281/zenodo.6517414, available under the Creative Commons Attribution 4.0 International License\r\nTrowitzsch, I., Taghia, J., Kashef, Y., & Obermayer, K. (2019). NIGENS general sound events data","description_withheld":null,"homepage":"https://zenodo.org/records/10811797","introduced_date":"2024-03-13","introduced_date_note":null,"introduced_by":{"paper":"/paper/from-weak-to-strong-sound-event-labels-using","title":"From Weak to Strong Sound Event Labels using Adaptive Change-Point Detection and Active Learning","first_author":"John Martinsson","url":null},"license":{"name":"CC BY-NC 4.0 LEGAL CODE","url":"https://creativecommons.org/licenses/by-nc/4.0/legalcode"},"modalities":[{"name":"Audio","url":"/datasets/modality/audio"}],"tasks":[{"name":"Sound Event Detection","url":"/task/sound-event-detection","datasets_with_task":"/datasets/task/sound-event-detection"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["BIOSED-ACPD"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}