{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:00:04Z","timestamp":1776888004846,"version":"3.51.2"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100009950","name":"Ministry of Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100009950","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100009950","name":"Ministry of Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100009950","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10887574","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["TS-SUPERB: A Target Speech Processing Benchmark for Speech Self-Supervised Learning Models"],"prefix":"10.1109","author":[{"given":"Junyi","family":"Peng","sequence":"first","affiliation":[{"name":"Brno University of Technology,Czechia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takanori","family":"Ashihara","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marc","family":"Delcroix","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tsubasa","family":"Ochiai","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Oldrich","family":"Plchot","sequence":"additional","affiliation":[{"name":"Brno University of Technology,Czechia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shoko","family":"Araki","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jan","family":"\u010cernock\u00fd","sequence":"additional","affiliation":[{"name":"Brno University of Technology,Czechia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"12 449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref2","first-page":"1298","article-title":"data2vec: A general framework for self-supervised learning in speech, vision and language","volume-title":"ICML","author":"Baevski"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389795"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747814"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022775"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023356"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10002"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.580"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-1316"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389699"},{"key":"ref14","first-page":"6890","article-title":"AVSUPERB: A multi-task evaluation benchmark for audio-visual representation models","author":"Tseng","year":"2024","journal-title":"ICASSP"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/slt61566.2024.10832296"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2023.3240008"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746962"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383600"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-62"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642057"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11425"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448315"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097139"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-453"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1280"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1242"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-556"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2024.101622"},{"key":"ref29","first-page":"125","article-title":"HAER: Holistic evaluation of audio representations","author":"Turian","year":"2022","journal-title":"NeurIPS 2021 Competitions and Demonstrations Track"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10007"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3428364"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097139"},{"key":"ref33","article-title":"LibriMix: An open-source dataset for generalizable speech separation","author":"Cosentino","year":"2020"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2821"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053426"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSPW62465.2024.10627502"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11252"},{"key":"ref39","first-page":"187","article-title":"KenLM: Faster and smaller language model queries","author":"Heafield","year":"2011","journal-title":"WMT"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683535"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054683"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.2307\/1412159"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10887574.pdf?arnumber=10887574","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:25Z","timestamp":1774416265000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10887574\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10887574","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}