{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:14:27Z","timestamp":1753600467769},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9747323","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"source":"Crossref","is-referenced-by-count":10,"title":["Endpoint Detection for Streaming End-to-End Multi-Talker ASR"],"prefix":"10.1109","author":[{"given":"Liang","family":"Lu","sequence":"first","affiliation":[{"name":"Otter.ai,Mountain View,CA,USA"}]},{"given":"Jinyu","family":"Li","sequence":"additional","affiliation":[{"name":"Microsoft Corp,USA"}]},{"given":"Yifan","family":"Gong","sequence":"additional","affiliation":[{"name":"Microsoft Corp,USA"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Continuous streaming multi-talker asr with dual-path transducers","author":"raj","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683109"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.940814"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178822"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6637694"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053896"},{"key":"ref16","article-title":"Transformer-transducer: End-to-end speech recognition with self-attention","author":"yeh","year":"2019"},{"key":"ref17","first-page":"449","article-title":"A comparative study on transformer vs rnn in speech applications","author":"karita","year":"2019","journal-title":"Proc ASRU"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413535"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461893"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2638"},{"key":"ref3","first-page":"6256","article-title":"End-to-end monaural multi-speaker asr system without pre-training","author":"chang","year":"2019","journal-title":"Proc ICASSP"},{"key":"ref6","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"2012"},{"key":"ref5","article-title":"Serialized output training for end-to-end overlapped speech recognition","author":"kanda","year":"2020"},{"key":"ref8","article-title":"Streaming end-to-end multi-talker speech recognition","author":"lu","year":"2020","journal-title":"IEEE Signal Processing Letters"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054328"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2284"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413471"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053426"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054715"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1085"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413803"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-207"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415062"},{"key":"ref26","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"IEEE ASRU"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09747323.pdf?arnumber=9747323","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:11:13Z","timestamp":1660594273000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747323\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747323","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}