{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:47:07Z","timestamp":1730231227056,"version":"3.28.0"},"reference-count":28,"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\/icassp48485.2024.10448052","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"11741-11745","source":"Crossref","is-referenced-by-count":0,"title":["Hubertopic: Enhancing Semantic Representation of Hubert Through Self-Supervision Utilizing Topic Model"],"prefix":"10.1109","author":[{"given":"Takashi","family":"Maekaku","sequence":"first","affiliation":[{"name":"LY Corporation,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiatong","family":"Shi","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,PA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuankai","family":"Chang","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,PA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuya","family":"Fujita","sequence":"additional","affiliation":[{"name":"LY Corporation,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,PA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.580"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688137"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022399"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-556"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1316"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10007"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26521"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3207050"},{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.1109\/ICASSP39728.2021.9414460","article-title":"HuBERT: How much can a bad teacher benefit ASR pre-training","volume-title":"NeurIPS Workshop on Self-Supervised Learning for Speech and Audio Processing","author":"Hsu"},{"key":"ref11","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"NeurIPS"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688253"},{"key":"ref14","first-page":"3915","article-title":"Self-supervised learning with random-projection quantizer for speech recognition","volume-title":"Proc. ICML","author":"Chiu"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094947"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095280"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-475"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1718"},{"key":"ref19","first-page":"18 003","article-title":"Contentvec: An improved self-supervised speech representation by disentangling speakers","volume-title":"Proc. ICML","author":"Qian"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-847"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096827"},{"issue":"Jan","key":"ref22","first-page":"993","article-title":"Latent dirichlet allocation","volume":"3","author":"Blei","year":"2003","journal-title":"JMLR"},{"key":"ref23","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL-HLT","author":"Kenton"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.108668"},{"article-title":"Bertopic: Neural topic modeling with a class-based tf-idf procedure","year":"2022","author":"Grootendorst","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2_7"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1456"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","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\/10448052.pdf?arnumber=10448052","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T06:40:58Z","timestamp":1722580858000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10448052\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10448052","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}