{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T12:57:44Z","timestamp":1725800264072},"reference-count":30,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,1,19]]},"DOI":"10.1109\/slt48900.2021.9383581","type":"proceedings-article","created":{"date-parts":[[2021,3,25]],"date-time":"2021-03-25T20:46:54Z","timestamp":1616705214000},"page":"75-81","source":"Crossref","is-referenced-by-count":13,"title":["Simplified Self-Attention for Transformer-Based end-to-end Speech Recognition"],"prefix":"10.1109","author":[{"given":"Haoneng","family":"Luo","sequence":"first","affiliation":[]},{"given":"Shiliang","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Ming","family":"Lei","sequence":"additional","affiliation":[]},{"given":"Lei","family":"Xie","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref30","DOI":"10.1109\/ASRU46091.2019.9003750"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref11","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"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1109\/ICASSP40776.2020.9053896"},{"key":"ref13","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"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.21437\/Interspeech.2019-2203"},{"key":"ref15","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc NIPS"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1109\/ICASSP.2018.8462497"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.21437\/Interspeech.2018-1910"},{"key":"ref18","first-page":"5884","article-title":"Speech-transformer: a no-recurrence sequence-to-sequence model for speech recognition","author":"dong","year":"2018","journal-title":"Proc ICASSP"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.21437\/Interspeech.2019-1938"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.21437\/Interspeech.2016-595"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1145\/1143844.1143891"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.18653\/v1\/P17-4012"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/ICASSP.2018.8462105"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.21437\/Interspeech.2018-1049"},{"doi-asserted-by":"publisher","key":"ref29","DOI":"10.1109\/ICASSP.2019.8682490"},{"year":"2014","author":"hannun","article-title":"Deep speech: Scaling up end-to-end speech recognition","key":"ref5"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref7","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Proc NIPS"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/TASL.2011.2134090"},{"year":"2012","author":"graves","article-title":"Sequence transduction with recurrent neural networks","key":"ref9"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1109\/MSP.2012.2205597"},{"year":"2019","author":"you","article-title":"DFSMN-SAN with persistent memory model for automatic speech recognition","key":"ref20"},{"year":"2019","author":"sukhbaatar","article-title":"Augmenting self-attention with persistent memory","key":"ref22"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.21437\/Interspeech.2019-2702"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1109\/ICSDA.2017.8384449"},{"year":"2015","author":"zhang","article-title":"Feedforward sequential memory networks: A new structure to learn long-term dependency","key":"ref23"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.21437\/Interspeech.2019-2680"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.1109\/ICASSP.2018.8461404"}],"event":{"name":"2021 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2021,1,19]]},"location":"Shenzhen, China","end":{"date-parts":[[2021,1,22]]}},"container-title":["2021 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9383468\/9383452\/09383581.pdf?arnumber=9383581","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,31]],"date-time":"2021-05-31T21:30:48Z","timestamp":1622496648000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9383581\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,19]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/slt48900.2021.9383581","relation":{},"subject":[],"published":{"date-parts":[[2021,1,19]]}}}