{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,30]],"date-time":"2025-08-30T16:25:06Z","timestamp":1756571106036,"version":"3.28.0"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"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":[[2019,10]]},"DOI":"10.1109\/waspaa.2019.8937250","type":"proceedings-article","created":{"date-parts":[[2019,12,24]],"date-time":"2019-12-24T06:50:13Z","timestamp":1577170213000},"page":"234-238","source":"Crossref","is-referenced-by-count":41,"title":["Speech Enhancement Using End-to-End Speech Recognition Objectives"],"prefix":"10.1109","author":[{"given":"Aswin Shanmugam","family":"Subramanian","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaofei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Murali Karthick","family":"Baskar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Toru","family":"Taniguchi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dung","family":"Tran","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuya","family":"Fujita","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1768"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.902460"},{"key":"ref31","article-title":"NARA-WPE: A Python package for weighted prediction error dereverberation in Numpy and Tensorflow for online and offline processing","author":"drude","year":"2018","journal-title":"ITG Fachtagung Sprachkommunikation"},{"article-title":"An investigation of end-to-end multichannel speech recognition for reverberant and mismatch conditions","year":"2019","author":"subramanian","key":"ref30"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"384","DOI":"10.21437\/Interspeech.2017-733","article-title":"Neural network-based spectrum estimation for online WPE dereverbertion","author":"kinoshita","year":"2017","journal-title":"InterSpeech"},{"key":"ref11","first-page":"5059","article-title":"Monaural speech enhancement using deep neural networks by maximizing a short-time objective intelligibility measure","author":"kolbcek","year":"2018","journal-title":"ICASSP"},{"key":"ref12","article-title":"Microphone array processing for robust speech recognition","author":"seltzer","year":"2003","journal-title":"PhD thesis"},{"key":"ref13","article-title":"Multichannel end-to-end speech recognition","author":"ochiai","year":"2017","journal-title":"ICML"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953173"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854051"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178797"},{"key":"ref17","first-page":"6745","article-title":"Joint training of complex ratio mask based beam-former and acoustic model for noise robust ASR","author":"xu","year":"2019","journal-title":"ICASSP"},{"year":"0","key":"ref18","article-title":"End to end multi channels system"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2210879"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-84996-056-4","author":"naylor","year":"2010","journal-title":"Speech Dereverberation"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404805"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2647702"},{"key":"ref6","first-page":"436","article-title":"Speech enhancement based on deep denoising autoencoder","author":"lu","year":"2013","journal-title":"InterSpeech"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639693"},{"key":"ref5","article-title":"Experiments on deep learning for speech denoising","author":"liu","year":"2014","journal-title":"InterSpeech"},{"key":"ref8","first-page":"1849","article-title":"On training targets for supervised speech separation","volume":"22","author":"wang","year":"2014","journal-title":"IEEE Trans on ASLP"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2364452"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1186\/s13634-016-0306-6"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178061"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1097\/AUD.0000000000000222"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2052251"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.911054"},{"key":"ref21","first-page":"1","article-title":"Does speech enhancement work with end-to-end ASR objectivesƒ: Experimental analysis of multichannel end-to-end ASR","author":"ochiai","year":"2017","journal-title":"MLSP"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2025790"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref26","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref25","article-title":"LSTM network supported linear filtering for the CHiME 2016 challenge","author":"wang","year":"2016","journal-title":"CHiME Workshop"}],"event":{"name":"2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","start":{"date-parts":[[2019,10,20]]},"location":"New Paltz, NY, USA","end":{"date-parts":[[2019,10,23]]}},"container-title":["2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8932990\/8937073\/08937250.pdf?arnumber=8937250","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T03:10:20Z","timestamp":1657854620000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8937250\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/waspaa.2019.8937250","relation":{},"subject":[],"published":{"date-parts":[[2019,10]]}}}