{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T17:41:47Z","timestamp":1776879707255,"version":"3.51.2"},"reference-count":31,"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\/icassp39728.2021.9413854","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"6024-6028","source":"Crossref","is-referenced-by-count":21,"title":["Tiny Transducer: A Highly-Efficient Speech Recognition Model on Edge Devices"],"prefix":"10.1109","author":[{"given":"Yuekai","family":"Zhang","sequence":"first","affiliation":[{"name":"Tencent Technology Co.,Ltd,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sining","family":"Sun","sequence":"additional","affiliation":[{"name":"Tencent Technology Co.,Ltd,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Long","family":"Ma","sequence":"additional","affiliation":[{"name":"Tencent Technology Co.,Ltd,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178778"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404790"},{"key":"ref10","article-title":"Fully neural network based speech recognition on mobile and embedded devices","author":"park","year":"2018","journal-title":"Neural"},{"key":"ref11","article-title":"Cascade rnn-transducer: Syllable based streaming on-device mandarin speech recognition with a syllable-to-character converter","author":"wang","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003750"},{"key":"ref14","article-title":"Simplified self-attention for transformer-based end-to-end speech recognition","author":"luo","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1209"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003775"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054419"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1221"},{"key":"ref19","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"2012"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2545928"},{"key":"ref3","article-title":"Recent developments on espnet toolkit boosted by conformer","author":"guo","year":"2020"},{"key":"ref6","article-title":"Sequence discriminative training of deep neural networks","author":"ghoshal","year":"2013","journal-title":"InterSpeech"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3016"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054188"},{"key":"ref7","article-title":"A time delay neural network architecture for efficient modeling of long temporal contexts","author":"peddinti","year":"2015","journal-title":"InterSpeech"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023133"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682336"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-121"},{"key":"ref21","article-title":"Feedforward sequential memory networks: A new structure to learn longterm dependency","author":"zhang","year":"2015"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2625459"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461404"},{"key":"ref26","first-page":"2365","article-title":"Restructuring of deep neural network acoustic models with singular value decomposition","author":"xue","year":"2013","journal-title":"InterSpeech"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003822"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Toronto, ON, Canada","start":{"date-parts":[[2021,6,6]]},"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\/09413854.pdf?arnumber=9413854","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,3]],"date-time":"2022-08-03T00:20:28Z","timestamp":1659486028000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9413854\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9413854","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}