{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T08:00:35Z","timestamp":1764403235040},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,12,11]],"date-time":"2022-12-11T00:00:00Z","timestamp":1670716800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,11]],"date-time":"2022-12-11T00:00:00Z","timestamp":1670716800000},"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":[[2022,12,11]]},"DOI":"10.1109\/iscslp57327.2022.10037796","type":"proceedings-article","created":{"date-parts":[[2023,2,8]],"date-time":"2023-02-08T13:53:24Z","timestamp":1675864404000},"page":"145-149","source":"Crossref","is-referenced-by-count":3,"title":["Speech-enhanced and Noise-aware Networks for Robust Speech Recognition"],"prefix":"10.1109","author":[{"given":"Hung-Shin","family":"Lee","sequence":"first","affiliation":[{"name":"Institute of Information Science,Academia Sinica"}]},{"given":"Pin-Yuan","family":"Chen","sequence":"additional","affiliation":[{"name":"Institute of Information Science,Academia Sinica"}]},{"given":"Yao-Fei","family":"Cheng","sequence":"additional","affiliation":[{"name":"Institute of Information Science,Academia Sinica"}]},{"given":"Yu","family":"Tsao","sequence":"additional","affiliation":[{"name":"Research Center for Information Technology Innovation,Academia Sinica"}]},{"given":"Hsin-Min","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Information Science,Academia Sinica"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Joint training of frontend and back-end deep neural networks for robust speech recognition","author":"gao","year":"2015","journal-title":"Proc ICASSP"},{"key":"ref35","article-title":"The design for the Wall Street Journal-based CSR corpus","author":"paul","year":"1992","journal-title":"Proc HLT"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref34","article-title":"The AMI meeting corpus: A preannouncement","author":"carletta","year":"2006","journal-title":"Proc MLMI"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462093"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-711"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-388"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1979.1163209"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2020-7"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1717"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682556"},{"key":"ref33","article-title":"Aurora Working Group: DSR front end LVCSR evaluation AU\/384\/02","author":"parihar","year":"2002","journal-title":"Inst Signal Inform Process Mississippi State Univ"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-84"},{"key":"ref32","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"Proc IEEE ASRU"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390294"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3039600"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2172"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461446"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1242"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472634"},{"key":"ref18","article-title":"Joint noise adaptive training for robust automatic speech recognition","author":"narayanan","year":"2015","journal-title":"Proc ICASSP"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1417"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-647"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2848701"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-548"},{"article-title":"Frustratingly easy Noise-aware training of acoustic models","year":"2020","author":"raj","key":"ref20"},{"key":"ref41","article-title":"On the robustness and training dynamics of raw waveform models","author":"loweimi","year":"2020","journal-title":"Proc INTERSPEECH"},{"key":"ref22","article-title":"JHU Aspire Syatem: Robust LVCSR with TDNNs, ivector adaptation and RNN-LMS","author":"peddinti","year":"2015","journal-title":"Proc IEEE ASRU"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-595"},{"key":"ref28","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc NeurIPS"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2020-9"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-221"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2528171"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2416653"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639100"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639038"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1270"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023216"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1428","article-title":"SEGAN: speech enhancement generative adversarial network","author":"pascual","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462629"}],"event":{"name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","start":{"date-parts":[[2022,12,11]]},"location":"Singapore, Singapore","end":{"date-parts":[[2022,12,14]]}},"container-title":["2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10037756\/10037573\/10037796.pdf?arnumber=10037796","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,6]],"date-time":"2023-03-06T13:37:14Z","timestamp":1678109834000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10037796\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,11]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/iscslp57327.2022.10037796","relation":{},"subject":[],"published":{"date-parts":[[2022,12,11]]}}}