{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T05:26:21Z","timestamp":1730265981223,"version":"3.28.0"},"reference-count":18,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"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":[[2021,7,18]]},"DOI":"10.1109\/ijcnn52387.2021.9533348","type":"proceedings-article","created":{"date-parts":[[2021,9,20]],"date-time":"2021-09-20T21:27:41Z","timestamp":1632173261000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["End-to-end speech recognition with Alignment RNN-Transducer"],"prefix":"10.1109","author":[{"given":"Ying","family":"Tian","sequence":"first","affiliation":[{"name":"Research & Development Center Toshiba(China) Co., Ltd,Beijing,China"}]},{"given":"Zerui","family":"Li","sequence":"additional","affiliation":[{"name":"School of Electronic Engineering Beijing University of Posts and Telecommunications,Beijing,China"}]},{"given":"Min","family":"Liu","sequence":"additional","affiliation":[{"name":"Research & Development Center Toshiba(China) Co., Ltd,Beijing,China"}]},{"given":"Kazushige","family":"Ouchi","sequence":"additional","affiliation":[{"name":"Research & Development Center Toshiba(China) Co., Ltd,Beijing,China"}]},{"given":"Long","family":"Yan","sequence":"additional","affiliation":[{"name":"Research & Development Center Toshiba(China) Co., Ltd,Beijing,China"}]},{"given":"Dan","family":"Zhao","sequence":"additional","affiliation":[{"name":"College of Information Engineering Capital Normal University,Beijing,China"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639690"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1341"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-275"},{"key":"ref14","first-page":"8026","article-title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library[J]","volume":"32","author":"paszke","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref15","article-title":"The Kaldi speech recognition toolkit[C]","author":"povey","year":"0","journal-title":"2011 IEEE Workshop on Automatic Speech Recognition & Understanding"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682500"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1117"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4842-2766-4_12"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1038"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"ii","DOI":"10.1109\/ICASSP.2003.1202279","article-title":"Hidden markov model-based speech emotion recognition[C]","volume":"2","author":"schuller","year":"0","journal-title":"2003 IEEE International Conference on Acoustics Speech and Signal Processing 2003 Proceedings (ICASSP‘03)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462492"},{"key":"ref8","article-title":"Sequence transduction with recurrent neural networks[J]","author":"graves","year":"2012","journal-title":"ArXiv Preprint"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"939","DOI":"10.21437\/Interspeech.2017-233","article-title":"A comparison of sequence-to-sequence models for speech rrecognition[C]","author":"prabhavalkar","year":"2017","journal-title":"InterSpeech"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-08-051584-7.50027-9"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICACCS.2015.7324119"},{"key":"ref9","first-page":"193","article-title":"Exploring architectures, data and units for streaming end-to-end speech recognition with rnn- transducer[C]","author":"rao","year":"0","journal-title":"Automatic Speech Recognition and Understanding (ASRU) 2017 IEEE Workshop on"}],"event":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2021,7,18]]},"location":"Shenzhen, China","end":{"date-parts":[[2021,7,22]]}},"container-title":["2021 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9533266\/9533267\/09533348.pdf?arnumber=9533348","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,2]],"date-time":"2022-08-02T23:32:30Z","timestamp":1659483150000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9533348\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,18]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/ijcnn52387.2021.9533348","relation":{},"subject":[],"published":{"date-parts":[[2021,7,18]]}}}