{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T04:39:34Z","timestamp":1780634374132,"version":"3.54.1"},"reference-count":19,"publisher":"IEEE","license":[{"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.2019.8683109","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T16:01:56Z","timestamp":1555516916000},"page":"5626-5630","source":"Crossref","is-referenced-by-count":22,"title":["Joint Endpointing and Decoding with End-to-end Models"],"prefix":"10.1109","author":[{"given":"Shuo-Yiin","family":"Chang","sequence":"first","affiliation":[{"name":"Google Inc, U.S.A"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rohit","family":"Prabhavalkar","sequence":"additional","affiliation":[{"name":"Google Inc, U.S.A"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanzhang","family":"He","sequence":"additional","affiliation":[{"name":"Google Inc, U.S.A"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tara N.","family":"Sainath","sequence":"additional","affiliation":[{"name":"Google Inc, U.S.A"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gabor","family":"Simko","sequence":"additional","affiliation":[{"name":"Google Inc, U.S.A"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"2012","journal-title":"CoRR"},{"key":"ref11","article-title":"Speech recognition with deep neural networks","author":"graves","year":"2012","journal-title":"Proc ICASSP"},{"key":"ref12","first-page":"4835","article-title":"Joint CTC-attention based end-to-end speech recognition using multi-task learning","author":"kim","year":"2017","journal-title":"Proc ICASSP"},{"key":"ref13","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":"Proc ASRU"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref15","article-title":"Generated of large-scale simulated utterances in virtual rooms to train deep-neural networks for far-field speech recognition in google home","author":"kim","year":"2017","journal-title":"Proc In-terspeech"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref17","article-title":"Layer Normalization","author":"ba","year":"2016","journal-title":"CoRR"},{"key":"ref18","article-title":"TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems","author":"abadi","year":"2015"},{"key":"ref19","article-title":"Convo-lutional, long short-term memory, fully connected deep neural networks","author":"sainath","year":"2015","journal-title":"Proc ICASSP"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461921"},{"key":"ref3","article-title":"All for one: feature combination for highly channel-degraded speech activity detection","author":"graciarena","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-284"},{"key":"ref5","article-title":"Improved end-of-query detection for streaming speech recognition","author":"simko","year":"2017","journal-title":"InterSpeech"},{"key":"ref8","article-title":"Listen, attend and spell","author":"chan","year":"2015","journal-title":"CoRR"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461478"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178822"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-268"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Brighton, UK","start":{"date-parts":[[2019,5,12]]},"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\/08683109.pdf?arnumber=8683109","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T18:18:58Z","timestamp":1755800338000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8683109\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8683109","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}