{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T21:42:52Z","timestamp":1760132572649,"version":"3.28.0"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8682273","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T20:01:56Z","timestamp":1555531316000},"page":"6630-6634","source":"Crossref","is-referenced-by-count":19,"title":["Acoustic Modeling for Distant Multi-talker Speech Recognition with Single- and Multi-channel Branches"],"prefix":"10.1109","author":[{"given":"Naoyuki","family":"Kanda","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yusuke","family":"Fujita","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shota","family":"Horiguchi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rintaro","family":"Ikeshita","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kenji","family":"Nagamatsu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1323"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707705"},{"key":"ref33","article-title":"Vocal tract length perturbation (VTLP) improves speech recognition","volume":"117","author":"jaitly","year":"2013","journal-title":"ICML Workshop on Deep Learning for Audio Speech and Language Processing"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref31","first-page":"3214","article-title":"A time delay neural network architecture for efficient modeling of long temporal contexts","author":"peddinti","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref30","first-page":"2632","article-title":"Multichannel end-to-end speech recognition","author":"ochiai","year":"2017","journal-title":"Proc ICML"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref36","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"Proc ASRU"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref34","first-page":"3586","article-title":"Audio augmentation for speech recognition","author":"ko","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref10","first-page":"309","article-title":"Elastic spectral distortion for low resource speech recognition with deep neural networks","author":"kanda","year":"2013","journal-title":"Proc ASRU"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2052251"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"2345","DOI":"10.21437\/Interspeech.2013-548","article-title":"Sequence-discriminative training of deep neural networks","author":"vesely","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638951"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-595"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268918"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-805"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2017.2723507"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471664"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-552"},{"key":"ref19","first-page":"31","article-title":"Deep clustering: Discriminative embeddings for segmentation and separation","author":"hershey","year":"2016","journal-title":"Proc ICASSP"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461580"},{"article-title":"Achieving human parity in conversational speech recognition","year":"2016","author":"xiong","key":"ref4"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2672401"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref6","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in English and Mandarin","author":"amodei","year":"2016","journal-title":"Proc ICML"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461533"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"132","DOI":"10.21437\/Interspeech.2017-405","article-title":"English conversational telephone speech recognition by humans and machines","author":"saon","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2284"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-79"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1768"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"437","DOI":"10.21437\/Interspeech.2011-169","article-title":"Conversational speech transcription using context-dependent deep neural networks","author":"seide","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-667"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462507"},{"key":"ref42","first-page":"28","article-title":"The AMI meeting corpus: A pre-announcement","author":"carletta","year":"2005","journal-title":"5th International Workshop on Machine Learning for Multimodal Interaction"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2018-2"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.902460"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462661"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472778"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2014.2325781"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2019,5,12]]},"location":"Brighton, United Kingdom","end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08682273.pdf?arnumber=8682273","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,17]],"date-time":"2024-07-17T00:55:25Z","timestamp":1721177725000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8682273\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8682273","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}