{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T18:42:48Z","timestamp":1747680168742,"version":"3.28.0"},"reference-count":25,"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\/icassp43922.2022.9746873","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T15:50:34Z","timestamp":1651074634000},"page":"6977-6981","source":"Crossref","is-referenced-by-count":2,"title":["VADOI: Voice-Activity-Detection Overlapping Inference for End-To-End Long-Form Speech Recognition"],"prefix":"10.1109","author":[{"given":"Jinhan","family":"Wang","sequence":"first","affiliation":[{"name":"University of California Los Angeles,Department of Electrical and Computer Engineering,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaosu","family":"Tong","sequence":"additional","affiliation":[{"name":"Amazon Alexa,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinxi","family":"Guo","sequence":"additional","affiliation":[{"name":"Amazon Alexa,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Di","family":"He","sequence":"additional","affiliation":[{"name":"Amazon Alexa,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roland","family":"Maas","sequence":"additional","affiliation":[{"name":"Amazon Alexa,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003854"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383518"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003913"},{"article-title":"Long-running speech recognizer: An end-to-end multi-task learning frame-work for online asr and vad","year":"2021","author":"li","key":"ref13"},{"article-title":"Improving generalization of transformer for speech recognition with parallel schedule sampling and relative positional embedding","year":"2019","author":"zhou","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414941"},{"key":"ref16","article-title":"Microsoft speech language translation (mslt) corpus: The iwslt 2016 release for english, french and german","author":"federmann","year":"2016","journal-title":"IWSLT"},{"key":"ref17","first-page":"5206","article-title":"Librispeech: an asr corpus based on public domain au-dio books","author":"panayotov","year":"2015","journal-title":"ICASSP"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.225858"},{"key":"ref19","first-page":"69","article-title":"The fisher corpus: A resource for the next generations of speech-to-text","volume":"4","author":"cieri","year":"2004","journal-title":"LREC"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref3","first-page":"5884","article-title":"Speech-transformer: a no-recurrence sequence-to-sequence model for speech recognition","author":"dong","year":"2018","journal-title":"ICASSP"},{"article-title":"Sequence transduction with recurrent neural networks","year":"2012","author":"graves","key":"ref6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2404"},{"article-title":"Neural machine translation by jointly learning to align and translate","year":"2014","author":"bahdanau","key":"ref8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414607"},{"key":"ref2","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","author":"graves","year":"2014","journal-title":"ICML"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1780"},{"key":"ref20","first-page":"265","article-title":"Tensorflow: A system for large-scale machine learning","author":"abadi","year":"2016","journal-title":"12th USENIX Symposium on Operating Systems Design and Implementation ( OSDI 16)"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413803"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404793"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/97.736233"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2022,5,23]]},"location":"Singapore, Singapore","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\/09746873.pdf?arnumber=9746873","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T16:07:31Z","timestamp":1660579651000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746873\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746873","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}