{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T15:07:11Z","timestamp":1725808031677},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"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":[[2023,1,9]]},"DOI":"10.1109\/slt54892.2023.10022813","type":"proceedings-article","created":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T13:54:03Z","timestamp":1674827643000},"page":"317-323","source":"Crossref","is-referenced-by-count":3,"title":["Learning Mask Scalars for Improved Robust Automatic Speech Recognition"],"prefix":"10.1109","author":[{"given":"Arun","family":"Narayanan","sequence":"first","affiliation":[{"name":"Google LLC,U.S.A."}]},{"given":"James","family":"Walker","sequence":"additional","affiliation":[{"name":"Google LLC,U.S.A."}]},{"given":"Sankaran","family":"Panchapagesan","sequence":"additional","affiliation":[{"name":"Google LLC,U.S.A."}]},{"given":"Nathan","family":"Howard","sequence":"additional","affiliation":[{"name":"Google LLC,U.S.A."}]},{"given":"Yuma","family":"Koizumi","sequence":"additional","affiliation":[{"name":"Google LLC,U.S.A."}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462116"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1484"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2998279"},{"key":"ref34","article-title":"Lingvo: a modular and scalable framework for sequence-to-sequence modeling","author":"shen","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471664"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053266"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639038"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054188"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3178115"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1108\/RR-08-2013-0197"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413899"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682460"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462372"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3039600"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383624"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413585"},{"key":"ref23","article-title":"SNRi target training for joint speech enhancement and recognition","author":"koizumi","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO54536.2021.9616081"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854051"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2253"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-318"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746347"},{"key":"ref28","article-title":"Cleanformer: A multichannel, streaming, microphone array configuration-invariant neural enhancement frontend for asr","author":"pundak","year":"0","journal-title":"Under review IEEE-SLT"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-275"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682682"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref7","article-title":"BigSSL: Exploring the frontier of large-scale semi-supervised learning for automatic speech recognition","author":"zhang","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1510"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1768"},{"key":"ref3","article-title":"Recent advances in end-to-end automatic speech recognition","author":"li","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2831"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639610"}],"event":{"name":"2022 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2023,1,9]]},"location":"Doha, Qatar","end":{"date-parts":[[2023,1,12]]}},"container-title":["2022 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10022052\/10022330\/10022813.pdf?arnumber=10022813","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,20]],"date-time":"2023-02-20T17:08:52Z","timestamp":1676912932000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10022813\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,9]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/slt54892.2023.10022813","relation":{},"subject":[],"published":{"date-parts":[[2023,1,9]]}}}