{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:29:48Z","timestamp":1775230188311,"version":"3.50.1"},"reference-count":37,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,12]]},"DOI":"10.1109\/slt.2018.8639593","type":"proceedings-article","created":{"date-parts":[[2019,2,14]],"date-time":"2019-02-14T23:36:34Z","timestamp":1550187394000},"page":"558-565","source":"Crossref","is-referenced-by-count":82,"title":["Multi-Channel Overlapped Speech Recognition with Location Guided Speech Extraction Network"],"prefix":"10.1109","author":[{"given":"Zhuo","family":"Chen","sequence":"first","affiliation":[]},{"given":"Xiong","family":"Xiao","sequence":"additional","affiliation":[]},{"given":"Takuya","family":"Yoshioka","sequence":"additional","affiliation":[]},{"given":"Hakan","family":"Erdogan","sequence":"additional","affiliation":[]},{"given":"Jinyu","family":"Li","sequence":"additional","affiliation":[]},{"given":"Yifan","family":"Gong","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2263137"},{"key":"ref31","article-title":"Neural network based time-frequency masking and steering vector estimation for two-channel mvdr beamforming","author":"yuzhou","year":"2018","journal-title":"Acoustics Speech and Signal Processing (ICASSP) 2018 IEEE International Conference on"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"399","DOI":"10.21437\/Interspeech.2017-234","article-title":"Acoustic modeling for google home","author":"li","year":"2017","journal-title":"Proc Interspeech 2017"},{"key":"ref37","article-title":"Analysis of overlaps in meetings by dialog factors, hot spots, speakers, and collection site: insights for automatic speech recognition","year":"2006","journal-title":"Ninth International Conference on Spoken Language Processing"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1121\/1.2799929"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404837"},{"key":"ref34","article-title":"Musan: A music, speech, and noise corpus","author":"snyder","year":"2015"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462081"},{"key":"ref11","first-page":"1981","article-title":"Improved mvdr beamforming using single-channel mask prediction networks","author":"erdogan","year":"2016","journal-title":"InterSpeech"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952756"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462661"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1109\/ASRU.2017.8268910","article-title":"Learning speaker representation for neural network based multichannel speaker extraction","author":"\u017emol\u00edkov\u00e1","year":"2017","journal-title":"Automatic Speech Recognition and Understanding (ASRU) 2017 IEEE Workshop on"},{"key":"ref15","doi-asserted-by":"crossref","DOI":"10.1145\/3197517.3201357","article-title":"Looking to listen at the cocktail party: A speaker-independent audio-visual model for speech separation","author":"ephrat","year":"2018"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461939"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461639"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-667","article-title":"Speaker-aware neural network based beamformer for speaker extraction in speech mixtures","author":"zmolikova","year":"2017","journal-title":"InterSpeech"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1400"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2284"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952155"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2672401"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1176"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2210879"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2726762"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"437","DOI":"10.1109\/ASRU.2017.8268969","article-title":"Cracking the cocktail party problem by multi-beam deep attractor network","author":"chen","year":"2017","journal-title":"IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-405","article-title":"English conversational telephone speech recognition by humans and machines","author":"saon","year":"2017"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/89.841206"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2756440"},{"key":"ref20","article-title":"Efficient integration of fixed beamformers and speech separation networks for multi-channel farfield speech separation","author":"chen","year":"2018","journal-title":"Acoustics Speech and Signal Processing (ICASSP) 2018 IEEE International Conference on"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178484"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461370"},{"key":"ref24","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-515","article-title":"Improving mask learning based speech enhancement system with restoration layers and residual connection","author":"chen","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2016.7738817"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/GlobalSIP.2014.7032183"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1007\/978-3-319-22482-4_11","article-title":"Speech enhancement with lstm recurrent neural networks and its application to noise-robust asr","author":"weninger","year":"2015","journal-title":"International Conference on Latent Variable Analysis and Signal Separation"}],"event":{"name":"2018 IEEE Spoken Language Technology Workshop (SLT)","location":"Athens, Greece","start":{"date-parts":[[2018,12,18]]},"end":{"date-parts":[[2018,12,21]]}},"container-title":["2018 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8632666\/8639030\/08639593.pdf?arnumber=8639593","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T03:00:53Z","timestamp":1643252453000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8639593\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/slt.2018.8639593","relation":{},"subject":[],"published":{"date-parts":[[2018,12]]}}}