{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,15]],"date-time":"2025-08-15T00:12:00Z","timestamp":1755216720706,"version":"3.43.0"},"reference-count":48,"publisher":"IEEE","license":[{"start":{"date-parts":[[2018,11,1]],"date-time":"2018-11-01T00:00:00Z","timestamp":1541030400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2018,11,1]],"date-time":"2018-11-01T00:00:00Z","timestamp":1541030400000},"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":[[2018,11]]},"DOI":"10.1109\/iscslp.2018.8706595","type":"proceedings-article","created":{"date-parts":[[2019,5,20]],"date-time":"2019-05-20T18:58:35Z","timestamp":1558378715000},"page":"21-25","source":"Crossref","is-referenced-by-count":6,"title":["Two-Stage Enhancement of Noisy and Reverberant Microphone Array Speech for Automatic Speech Recognition Systems Trained with Only Clean Speech"],"prefix":"10.1109","author":[{"given":"Quandong","family":"Wang","sequence":"first","affiliation":[{"name":"University of Chinese Academy of Sciences, Beijing, China"}]},{"given":"Sicheng","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences, Beijing, China"}]},{"given":"Fengpei","family":"Ge","sequence":"additional","affiliation":[{"name":"The Key Laboratory of Speech Acoustic and Content Understanding, Institute of Acoustics, China"}]},{"given":"Chang Woo","family":"Han","sequence":"additional","affiliation":[{"name":"Samsung Research, Samsung Electronics, Seoul, Korea"}]},{"given":"Jaewon","family":"Lee","sequence":"additional","affiliation":[{"name":"Samsung Research, Samsung Electronics, Seoul, Korea"}]},{"given":"Lianghao","family":"Guo","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Acoustics, Institute of Acoustics, Beijing, China"}]},{"given":"Chin-Hui","family":"Lee","sequence":"additional","affiliation":[{"name":"School of Electrical and Computer Engineering, Georgia Institute of Technology, GA, USA"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/HSCMA.2017.7895577"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471664"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1186\/s13634-017-0516-6"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2623559"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2558822"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2016.12.004"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404829"},{"key":"ref36","first-page":"482","article-title":"Robust ASR using neural network based speech enhancement and feature simulation","author":"sivasankaran","year":"2015","journal-title":"Proc IEEE Workshop ASRU"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472671"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-579"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/78.934132"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639038"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2004.07.028"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2007.02.001"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2025790"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2090519"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1969.7278"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2010.5417174"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1987.1165142"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2009.5346463"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/78.972477"},{"key":"ref28","first-page":"101","article-title":"Joint noise and mask aware training for DNN-based speech enhancement with SUBband features","author":"wang","year":"2017","journal-title":"Proc HSCMA"},{"journal-title":"Microphone Array Signal Processing","year":"2008","author":"benesty","key":"ref4"},{"key":"ref27","first-page":"1508","article-title":"Multi-objective Learning and Mask-based Post-processing for Deep Neural Network based Speech Enhancement","author":"xu","year":"2015","journal-title":"InterSpeech"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1201\/b14529"},{"journal-title":"Trees Optimum Array Processing Part IV of Detection Estimation and Modulation Theory","year":"2004","author":"van","key":"ref6"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2017.8282081"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1002\/9780470714089"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TAP.1982.1142739"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1002\/0471733482"},{"journal-title":"Digital Processing of Speech Signals","year":"1978","author":"rabiner","key":"ref2"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/78.790650"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2647702"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1995.0010"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2010.2051803"},{"key":"ref45","first-page":"1","article-title":"Feature extraction methods LPC, PLP and MFCC in speech recognition","volume":"1","author":"dave","year":"2013","journal-title":"in Proc IJARET"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2191283"},{"journal-title":"Speech","year":"2010","author":"naylor","key":"ref22"},{"journal-title":"P 862 Perceptual evaluation of speech quality (PESQ) An objective method for end-to-end speech quality assessment of narrowband telephone networks and speech codecs Int Telecommun Union-Telecommun Stand Sector","year":"2001","key":"ref47"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2024731"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1121\/1.2936367"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2244086"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163353"},{"key":"ref23","first-page":"1218","article-title":"New insights into the noise reduction Wiener filter","volume":"14","author":"chen","year":"2006","journal-title":"IEEE Trans"},{"journal-title":"100 nonspeech environmental sounds","year":"2004","author":"hu","key":"ref44"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1109\/TASLP.2014.2364452","article-title":"A regression approach to speech enhancement based on deep neural networks","author":"xu","year":"2015","journal-title":"IEEE Trans Audio Speech and Lang Proc"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.3115\/1075527.1075614"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2013.2291240"}],"event":{"name":"2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)","start":{"date-parts":[[2018,11,26]]},"location":"Taipei, Taiwan","end":{"date-parts":[[2018,11,29]]}},"container-title":["2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8701133\/8706262\/08706595.pdf?arnumber=8706595","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,4]],"date-time":"2025-08-04T18:42:17Z","timestamp":1754332937000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8706595\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/iscslp.2018.8706595","relation":{},"subject":[],"published":{"date-parts":[[2018,11]]}}}