{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:29:13Z","timestamp":1775230153723,"version":"3.50.1"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9054358","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"6999-7003","source":"Crossref","is-referenced-by-count":36,"title":["End-to-End Automatic Speech Recognition Integrated with CTC-Based Voice Activity Detection"],"prefix":"10.1109","author":[{"given":"Takenori","family":"Yoshimura","sequence":"first","affiliation":[]},{"given":"Tomoki","family":"Hayashi","sequence":"additional","affiliation":[]},{"given":"Kazuya","family":"Takeda","sequence":"additional","affiliation":[]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2860"},{"key":"ref32","article-title":"Enhancing the TED-LIUM corpus with selected data for language modeling and more TED talks","author":"rousseau","year":"2014","journal-title":"Proceedings of the 9th LREC"},{"key":"ref31","first-page":"7","article-title":"Corpus of spontaneous Japanese: Its design and evaluation","author":"maekawa","year":"0"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003750"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3192"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2316"},{"key":"ref12","first-page":"5067","article-title":"An online sequence-to- sequence model using partial conditioning","author":"jaitly","year":"2016","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"3692","DOI":"10.21437\/Interspeech.2017-751","article-title":"Gaussian prediction based attention for online end-to-end speech recognition","author":"hou","year":"2017","journal-title":"Proceedings of Interspeech"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2218"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2018"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683510"},{"key":"ref17","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"2012"},{"key":"ref18","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":"Proceedings of ASRU"},{"key":"ref19","article-title":"Streaming end-to-end speech recognition for mobile devices","author":"he","year":"2018"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"1492","DOI":"10.21437\/Interspeech.2012-422","article-title":"Voice activity detection using speech recognizer feedback","author":"thambiratnam","year":"2012","journal-title":"Proceedings of Interspeech"},{"key":"ref4","article-title":"End-to-end continuous speech recognition using attention-based recurrent NN: First results","author":"chorowski","year":"2014"},{"key":"ref3","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014"},{"key":"ref27","first-page":"22392242","article-title":"Robust speech recognition using VAD-measure- embedded decoder","author":"oonishi","year":"2009","journal-title":"Proceedings of Interspeech"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"949","DOI":"10.21437\/Interspeech.2017-1296","article-title":"Advances in joint CTC-attention based end-to-end speech recognition with a deep CNN encoder and RNN-LM","author":"hori","year":"2017","journal-title":"Proceedings of Interspeech"},{"key":"ref29","article-title":"Exploring RNN-transducer for Chinese speech recognition","author":"wang","year":"2018"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639044"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1616"},{"key":"ref2","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","author":"graves","year":"2014","journal-title":"Proc 31th ICML"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639643"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1976.1162800"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/97.736233"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.5772\/4740"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2229986"},{"key":"ref23","first-page":"173","article-title":"Noise robust real world spoken dialogue system using GMM based rejection of unintended inputs","author":"lee","year":"2004","journal-title":"Proceedings of 8th ICSLP"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639096"},{"key":"ref25","first-page":"728","article-title":"Speech activity detection on YouTube using deep neural networks","author":"ryant","year":"2013","journal-title":"Proceedings of Interspeech"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Barcelona, Spain","start":{"date-parts":[[2020,5,4]]},"end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09054358.pdf?arnumber=9054358","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,29]],"date-time":"2023-09-29T19:28:12Z","timestamp":1696015692000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9054358\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9054358","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}