{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T16:06:03Z","timestamp":1776441963225,"version":"3.51.2"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9747077","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"6152-6156","source":"Crossref","is-referenced-by-count":69,"title":["Unispeech-Sat: Universal Speech Representation Learning With Speaker Aware Pre-Training"],"prefix":"10.1109","author":[{"given":"Sanyuan","family":"Chen","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology,China"}]},{"given":"Yu","family":"Wu","sequence":"additional","affiliation":[{"name":"Microsoft Corporation"}]},{"given":"Chengyi","family":"Wang","sequence":"additional","affiliation":[{"name":"Microsoft Corporation"}]},{"given":"Zhengyang","family":"Chen","sequence":"additional","affiliation":[{"name":"Microsoft Corporation"}]},{"given":"Zhuo","family":"Chen","sequence":"additional","affiliation":[{"name":"Microsoft Corporation"}]},{"given":"Shujie","family":"Liu","sequence":"additional","affiliation":[{"name":"Microsoft Corporation"}]},{"given":"Jian","family":"Wu","sequence":"additional","affiliation":[{"name":"Microsoft Corporation"}]},{"given":"Yao","family":"Qian","sequence":"additional","affiliation":[{"name":"Microsoft Corporation"}]},{"given":"Furu","family":"Wei","sequence":"additional","affiliation":[{"name":"Microsoft Corporation"}]},{"given":"Jinyu","family":"Li","sequence":"additional","affiliation":[{"name":"Microsoft Corporation"}]},{"given":"Xiangzhan","family":"Yu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,China"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1228"},{"key":"ref11","article-title":"Non-autoregressive predictive coding for learning speech representations from local dependencies","author":"liu","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054458"},{"key":"ref13","article-title":"Tera: Self-supervised learning of transformer encoder representation for speech","author":"liu","year":"2020"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053569"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref17","article-title":"Gigaspeech: An evolving, multi-domain asr corpus with 10,000 hours of transcribed audio","author":"wang","year":"2021","journal-title":"Proc INTERSPEECH 2021"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.80"},{"key":"ref19","article-title":"Categorical reparameterization with gumbel-softmax","author":"jang","year":"2016"},{"key":"ref4","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","author":"baevski","year":"2020","journal-title":"ICLRE"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref5","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020","journal-title":"NeurIPS"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1473"},{"key":"ref7","article-title":"Bigssl: Exploring the frontier of large-scale semi-supervised learning for automatic speech recognition","author":"zhang","year":"2021"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054548"},{"key":"ref1","article-title":"Representation learning with contrastive predictive coding","author":"van den oord","year":"2018","journal-title":"CoRR"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054438"},{"key":"ref20","first-page":"5206","article-title":"Librispeech: An ASR corpus based on public domain audio books","author":"panayotov","year":"2015","journal-title":"ICASSP"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09747077.pdf?arnumber=9747077","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:06:45Z","timestamp":1660594005000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747077\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747077","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}