{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T13:13:22Z","timestamp":1725714802524},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9414598","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T15:53:45Z","timestamp":1620921225000},"page":"6743-6747","source":"Crossref","is-referenced-by-count":3,"title":["An Investigation of Using Hybrid Modeling Units for Improving End-to-End Speech Recognition System"],"prefix":"10.1109","author":[{"given":"Shunfei","family":"Chen","sequence":"first","affiliation":[{"name":"Hithink RoyalFlush AI Research Institute,Zhejiang,China"}]},{"given":"Xinhui","family":"Hu","sequence":"additional","affiliation":[{"name":"Hithink RoyalFlush AI Research Institute,Zhejiang,China"}]},{"given":"Sheng","family":"Li","sequence":"additional","affiliation":[{"name":"National Institute of Information and Communications Technology (NICT),Kyoto,Japan"}]},{"given":"Xinkang","family":"Xu","sequence":"additional","affiliation":[{"name":"Hithink RoyalFlush AI Research Institute,Zhejiang,China"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1109\/ISCSLP.2018.8706675"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1109\/ICASSP.2019.8683859"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1109\/ICASSP.2018.8462576"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.21437\/Interspeech.2016-334"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.21437\/Interspeech.2017-1118"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1109\/ICASSP.2017.7953075"},{"year":"2018","author":"krishna","article-title":"Hierarchical multitask learning for ctc-based speech recognition","key":"ref16"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.21437\/Interspeech.2019-2104"},{"key":"ref18","article-title":"Context dependent syllable acoustic model for continuous chinese speech recognition","author":"wu","year":"2007","journal-title":"Eighth Annual Conference of the International Speech Communication Association"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1109\/ICASSP.2012.6289079"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1109\/ICASSP40776.2020.9053165"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/ASRU46091.2019.9003750"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1109\/ISCSLP.2018.8706661"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/TASL.2011.2134090"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1109\/ICASSP.2018.8462105"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1007\/978-3-030-04221-9_19"},{"key":"ref2","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in english and mandarin","author":"amodei","year":"2016","journal-title":"International Conference on Machine Learning"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/ICASSP.2018.8462017"},{"year":"2014","author":"hannun","article-title":"Deep speech: Scaling up end-to-end speech recognition","key":"ref1"},{"year":"2015","author":"sennrich","article-title":"Neural machine translation of rare words with subword units","key":"ref20"},{"year":"0","article-title":"ST-CMDS-20170001 1, Free ST Chinese Mandarin Corpus","key":"ref22"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1145\/1143844.1143891"},{"year":"0","article-title":"aidatatang 200zh, a free Chinese Mandarin speech corpus","key":"ref24"},{"year":"2018","article-title":"Prime-words Chinese Corpus Set 1","key":"ref23"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1109\/ICSDA.2017.8384449"},{"year":"2019","article-title":"MAGICDATA Mandarin Chinese Read Speech Corpus","key":"ref25"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2021,6,6]]},"location":"Toronto, ON, Canada","end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09414598.pdf?arnumber=9414598","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,2]],"date-time":"2022-08-02T20:20:45Z","timestamp":1659471645000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414598\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414598","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}