{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:25:07Z","timestamp":1775229907491,"version":"3.50.1"},"reference-count":46,"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\/100002465","name":"Delta","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100002465","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","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\/icasspw65056.2025.11011236","type":"proceedings-article","created":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T17:05:14Z","timestamp":1748365514000},"page":"1-5","source":"Crossref","is-referenced-by-count":3,"title":["Discrete Speech Unit Extraction via Independent Component Analysis"],"prefix":"10.1109","author":[{"given":"Tomohiko","family":"Nakamura","sequence":"first","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kwanghee","family":"Choi","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keigo","family":"Hojo","sequence":"additional","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yoshiaki","family":"Bando","sequence":"additional","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Satoru","family":"Fukayama","sequence":"additional","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. NeurIPS","author":"Baevski"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-143"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.580"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1316"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448257"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688093"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096149"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448065"},{"key":"ref12","article-title":"Opening the black box of wav2vec feature encoder","author":"Choi","year":"2022"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1157"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1878"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447929"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.235"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.872"},{"key":"ref19","article-title":"AudioPaLM: A large language model that can speak and listen","author":"Rubenstein","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447112"},{"key":"ref21","article-title":"On generative spoken language modeling from raw audio","author":"Lakhotia","year":"2021","journal-title":"Trans. ACL"},{"key":"ref22","article-title":"Textually pretrained speech language models","volume-title":"Proc. NeurIPS","author":"Hassid"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746484"},{"key":"ref24","article-title":"Improved distributed principal component analysis","volume-title":"Proc. NeurIPS","author":"Liang"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096099"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10865"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1054"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.283"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688253"},{"key":"ref30","article-title":"Whitening sentence representations for better semantics and faster retrieval","author":"Su","year":"2021"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.23"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1017\/ATSIP.2019.5"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/97.566704"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15995-4_21"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref36","article-title":"The ChinaTelecom Interspeech2024 discrete speech unit asr challenge system description","author":"Li","year":"2024","journal-title":"Submission for Interspeech 2024 Challenge on Speech Processing Using Discrete Units"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2051"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022656"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1190\/1.9781560804048.ch13"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832364"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.63"},{"key":"ref42","article-title":"All-but-the-top: Simple and effective postprocessing for word representations","volume-title":"Proc. ICLR","author":"Mu"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-4328"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.6028\/NIST.IR.4930"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2131"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097097"}],"event":{"name":"2025 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["2025 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11010992\/11010997\/11011236.pdf?arnumber=11011236","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,28]],"date-time":"2025-05-28T04:54:36Z","timestamp":1748408076000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11011236\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/icasspw65056.2025.11011236","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}