{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:29:46Z","timestamp":1774420186095,"version":"3.50.1"},"reference-count":28,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889923","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":0,"title":["Learning Rich Speech Representations with Acoustic-Semantic Factorization"],"prefix":"10.1109","author":[{"given":"Minxue","family":"Niu","sequence":"first","affiliation":[{"name":"Amazon Prime Video"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Najmeh","family":"Sadoughi","sequence":"additional","affiliation":[{"name":"Amazon Prime Video"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abhishek","family":"Yanamandra","sequence":"additional","affiliation":[{"name":"Amazon Prime Video"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pichao","family":"Wang","sequence":"additional","affiliation":[{"name":"Amazon Prime Video"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhu","family":"Liu","sequence":"additional","affiliation":[{"name":"Amazon Prime Video"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vimal","family":"Bhat","sequence":"additional","affiliation":[{"name":"Amazon Prime Video"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"S. Elizabeth","family":"Norred","sequence":"additional","affiliation":[{"name":"Amazon Prime Video"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3207050"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref3","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"NeurIPS"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref5","article-title":"HEAR: Holistic evaluation of audio representations","author":"Turian","year":"2022"},{"key":"ref6","article-title":"Neural discrete representation learning","volume":"30","author":"Den Oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref7","article-title":"Representation learning with contrastive predictive coding","author":"den Oord","year":"2018"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096149"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688093"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-703"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2078"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29846"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP52302.2021.9596320"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-571"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591664"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-950"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9280.1995.tb00596.x"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/RADIOELEK.2019.8733432"},{"key":"ref24","article-title":"Speech commands: A dataset for limited-vocabulary speech recognition","author":"Warden","year":"2018"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref26","article-title":"Gaussian error linear units (gelus)","author":"Hendrycks","year":"2016"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.2985586"},{"key":"ref28","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2022"}],"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\/10889923.pdf?arnumber=10889923","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:52Z","timestamp":1774416412000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889923\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889923","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}