{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T14:05:47Z","timestamp":1730297147393,"version":"3.28.0"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"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":[[2023,1,9]]},"DOI":"10.1109\/slt54892.2023.10022528","type":"proceedings-article","created":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T13:54:03Z","timestamp":1674827643000},"page":"123-129","source":"Crossref","is-referenced-by-count":1,"title":["Pronunciation-Aware Unique Character Encoding for RNN Transducer-Based Mandarin Speech Recognition"],"prefix":"10.1109","author":[{"given":"Peng","family":"Shen","sequence":"first","affiliation":[{"name":"National Institute of Information and Communications Technology (NICT)"}]},{"given":"Xugang","family":"Lu","sequence":"additional","affiliation":[{"name":"National Institute of Information and Communications Technology (NICT)"}]},{"given":"Hisashi","family":"Kawai","sequence":"additional","affiliation":[{"name":"National Institute of Information and Communications Technology (NICT)"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2057"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683859"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688101"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383581"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461935"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054188"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1561\/116.00000050"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2018.8706661"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414598"},{"key":"ref19","article-title":"Sub-character tokenization for chinese pretrained language models","volume":"abs 2106 400","author":"si","year":"2021","journal-title":"ArXiv"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383506"},{"journal-title":"OpenSLR org\/68","article-title":"MAGICDATA: Mandarin chinese read speech corpus","year":"2019","key":"ref24"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref20","first-page":"1","article-title":"Using subcharacter level information for neural machine translation of logographic languages","volume":"20","author":"zhang","year":"2021","journal-title":"ACM Transactions on Asian and Low-Resource Language Information Processing"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414784"},{"key":"ref21","article-title":"Language model fusion for streaming end to end speech recognition","volume":"abs 2104 4487","author":"cabrera","year":"2021","journal-title":"ArXiv"},{"key":"ref28","article-title":"SGDR: Stochastic gradient descent with warm restarts","author":"loshchilov","year":"2017","journal-title":"Proc ICLR"},{"key":"ref27","article-title":"Stochastic gradient methods with layer-wise adaptive moments for training of deep networks","volume":"abs 1905 11286","author":"ginsburg","year":"2019","journal-title":"ArXiv"},{"key":"ref29","article-title":"NeMo: A toolkit for building ai applications using neural modules","author":"kuchaiev","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref8","article-title":"Towards end-to-end speech recognition with recurrent neural networks","author":"graves","year":"2014","journal-title":"Proc ICML"},{"journal-title":"Automatic Speech Recognition?A Deep Learning Approach","year":"2014","author":"yu","key":"ref7"},{"key":"ref9","article-title":"Deep speech: Scaling up end-to-end speech recognition","volume":"abs 1412 5567","author":"hannun","year":"2014","journal-title":"ArXiv"},{"key":"ref4","article-title":"End-to-end continuous speech recognition using attention-based recurrent NN: First results","author":"chorowski","year":"2014","journal-title":"Proc NeurIPS"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3016"},{"key":"ref6","article-title":"Sequence transduction with recurrent neural networks","author":"alex","year":"2012","journal-title":"Proc ICML"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"}],"event":{"name":"2022 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2023,1,9]]},"location":"Doha, Qatar","end":{"date-parts":[[2023,1,12]]}},"container-title":["2022 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10022052\/10022330\/10022528.pdf?arnumber=10022528","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,20]],"date-time":"2023-02-20T17:08:19Z","timestamp":1676912899000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10022528\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,9]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/slt54892.2023.10022528","relation":{},"subject":[],"published":{"date-parts":[[2023,1,9]]}}}