{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:40:19Z","timestamp":1776883219149,"version":"3.51.2"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447620","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"7505-7509","source":"Crossref","is-referenced-by-count":19,"title":["Positive Transfer of the Whisper Speech Transformer to Human and Animal Voice Activity Detection"],"prefix":"10.1109","author":[{"given":"Nianlong","family":"Gu","sequence":"first","affiliation":[{"name":"University of Zurich,Linguistic Research Infrastructure,Switzerland"}]},{"given":"Kanghwi","family":"Lee","sequence":"additional","affiliation":[{"name":"University of Zurich and ETH Zurich,Institute of Neuroinformatics,Switzerland"}]},{"given":"Maris","family":"Basha","sequence":"additional","affiliation":[{"name":"University of Zurich and ETH Zurich,Institute of Neuroinformatics,Switzerland"}]},{"given":"Sumit","family":"Kumar Ram","sequence":"additional","affiliation":[{"name":"University of Zurich,Linguistic Research Infrastructure,Switzerland"}]},{"given":"Guanghao","family":"You","sequence":"additional","affiliation":[{"name":"University of Zurich,Linguistic Research Infrastructure,Switzerland"}]},{"given":"Richard H. R.","family":"Hahnloser","sequence":"additional","affiliation":[{"name":"University of Zurich and ETH Zurich,Institute of Neuroinformatics,Switzerland"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"Voice activity detection algorithm for speech recognition applications","volume-title":"IJCA Proceedings on International Conference in Computational Intelligence (IC-CIA2012), vol. iccia","volume":"6","author":"Lokhande"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1602"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3389\/fcomp.2022.837269"},{"key":"ref4","first-page":"3155","article-title":"An acoustic analysis of nungon vowels in child-versus adult-directed speech","volume-title":"Proceedings of the 19th International Congress of Phonetic Sciences Melbourne","author":"Sarvasy"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1800708115"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.07770"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1892-x"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0288172"},{"key":"ref9","article-title":"Automatic sound event detection and classification of great ape calls using neural networks","author":"Jiang","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415081"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.63853"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.68837"},{"key":"ref13","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2022"},{"key":"ref14","article-title":"whisper-timestamped","author":"Louradour","year":"2023"},{"key":"ref15","article-title":"Benchmarking nearest neighbor retrieval of zebra finch vocalizations across development","author":"Tomka","year":"2023","journal-title":"bioRxiv"},{"key":"ref16","article-title":"Bengalese Finch song repository","author":"Nicholson","year":"2021"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0227392"},{"key":"ref18","article-title":"Classifying sex and strain from mouse ultrasonic vocalizations using deep learning","author":"Englitz","year":"2020"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2028"},{"key":"ref20","article-title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling","author":"Bai","year":"2018"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10447620.pdf?arnumber=10447620","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:53:12Z","timestamp":1722577992000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447620\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447620","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}