{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T10:08:29Z","timestamp":1767262109886,"version":"3.28.0"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10095591","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T13:28:30Z","timestamp":1683293310000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["DATA2VEC-SG: Improving Self-Supervised Learning Representations for Speech Generation Tasks"],"prefix":"10.1109","author":[{"given":"Heming","family":"Wang","sequence":"first","affiliation":[{"name":"The Ohio State University,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yao","family":"Qian","sequence":"additional","affiliation":[{"name":"Microsoft Corporation,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hemin","family":"Yang","sequence":"additional","affiliation":[{"name":"Microsoft Corporation,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nauyuki","family":"Kanda","sequence":"additional","affiliation":[{"name":"Microsoft Corporation,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peidong","family":"Wang","sequence":"additional","affiliation":[{"name":"Microsoft Corporation,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takuya","family":"Yoshioka","sequence":"additional","affiliation":[{"name":"Microsoft Corporation,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaofei","family":"Wang","sequence":"additional","affiliation":[{"name":"Microsoft Corporation,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiming","family":"Wang","sequence":"additional","affiliation":[{"name":"Microsoft Corporation,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shujie","family":"Liu","sequence":"additional","affiliation":[{"name":"Microsoft Corporation,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhuo","family":"Chen","sequence":"additional","affiliation":[{"name":"Microsoft Corporation,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"DeLiang","family":"Wang","sequence":"additional","affiliation":[{"name":"The Ohio State University,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Zeng","sequence":"additional","affiliation":[{"name":"Microsoft Corporation,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413555"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10002"},{"key":"ref15","article-title":"FAIRSEQ: A fast, extensible toolkit for sequence modeling","author":"myle","year":"2019","journal-title":"Proceedings NAACL-HLT Demonstrations"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053569"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746303"},{"key":"ref10","first-page":"749","article-title":"Perceptual evaluation of speech quality (PESQ)-a new method for speech quality assessment of telephone networks and codecs","author":"rix","year":"2001","journal-title":"Proceedings of ICASSP"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1473"},{"key":"ref1","article-title":"Data2vec: A general framework for self-supervised learning in speech, vision and language","author":"baevski","year":"2022","journal-title":"arXiv 2202 03555 [cs]"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3038"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2726762"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2013.6709856"},{"key":"ref24","first-page":"626","article-title":"SDR– half-baked or well doneƒ","author":"le roux","year":"2019","journal-title":"Proceedings of ICASSP"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10962"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10829"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415105"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(93)90095-3"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2537"},{"key":"ref28","first-page":"187","article-title":"KenLM: Faster and smaller language model queries","author":"heafield","year":"2011","journal-title":"Proceedings of the statistical machine translation"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref29","article-title":"MUSAN: A music, speech, and noise corpus","author":"snyder","year":"2015","journal-title":"arXiv 1510 08484 [cs]"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.580"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref4","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":"Advances in neural information processing systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054458"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747077"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10095591.pdf?arnumber=10095591","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T14:03:19Z","timestamp":1700488999000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095591\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095591","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}