{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T02:02:23Z","timestamp":1769911343548,"version":"3.49.0"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9414955","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"6908-6912","source":"Crossref","is-referenced-by-count":5,"title":["Improving RNN Transducer with Target Speaker Extraction and Neural Uncertainty Estimation"],"prefix":"10.1109","author":[{"given":"Jiatong","family":"Shi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunlei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chao","family":"Weng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meng","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dong","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2450497"},{"key":"ref32","first-page":"181","article-title":"Speech enhancement using self-adaptation and multi-head self-attention","author":"koizumi","year":"2020","journal-title":"ICASSP"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268934"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/HSCMA.2017.7895555"},{"key":"ref34","article-title":"Aishell-2: transforming mandarin asr research into industrial scale","author":"du","year":"2018"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1193"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854051"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178797"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953173"},{"key":"ref14","first-page":"2632","article-title":"Multichannel end-to-end speech recognition","author":"ochiai","year":"2017","journal-title":"ICML"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461893"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053692"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682576"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2020-2519","article-title":"Multi-talker asr for an unknown number of sources: Joint training of source counting, separation and asr","author":"von neumann","year":"2020"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.845814"},{"key":"ref28","first-page":"193","article-title":"Exploring architectures, data and units for streaming end-to-end speech recognition with rnn-transducer","author":"rao","year":"2017","journal-title":"ASRU"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2558822"},{"key":"ref27","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"2012"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2536478"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462661"},{"key":"ref29","article-title":"Uncertainty propagation through deep neural networks","author":"abdelaziz","year":"2015","journal-title":"InterSpeech"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"2655","DOI":"10.21437\/Interspeech.2017-667","article-title":"Speaker-aware neural network based beam- former for speaker extraction in speech mixtures","author":"zmolikova","year":"2017","journal-title":"InterSpeech"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1101"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2922820"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1531"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054311"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1570"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854657"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2831456"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"1487","DOI":"10.21437\/Interspeech.2017-1608","article-title":"End-to-end text-independent speaker verification with triplet loss on short utterances","author":"zhang","year":"2017","journal-title":"InterSpeech"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003750"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2702"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Toronto, ON, Canada","start":{"date-parts":[[2021,6,6]]},"end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09414955.pdf?arnumber=9414955","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:41:07Z","timestamp":1652197267000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414955\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414955","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}