{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T13:20:17Z","timestamp":1725715217961},"reference-count":45,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746406","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"8107-8111","source":"Crossref","is-referenced-by-count":3,"title":["Transducer-Based Streaming Deliberation for Cascaded Encoders"],"prefix":"10.1109","author":[{"given":"Ke","family":"Hu","sequence":"first","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Tara N.","family":"Sainath","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Arun","family":"Narayanan","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Ruoming","family":"Pang","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Trevor","family":"Strohman","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref39","DOI":"10.1137\/0330046"},{"year":"2019","author":"shen","article-title":"Lingvo: A modular and scalable framework for sequence-to-sequence modeling","key":"ref38"},{"doi-asserted-by":"publisher","key":"ref33","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref32","first-page":"1784","article-title":"Deliberation networks: Sequence generation beyond one-pass decoding","author":"xia","year":"2017","journal-title":"Advances in neural information processing systems"},{"doi-asserted-by":"publisher","key":"ref31","DOI":"10.21437\/Interspeech.2021-212"},{"year":"2012","author":"graves","article-title":"Sequence transduction with recurrent neural networks","key":"ref30"},{"key":"ref37","first-page":"265","article-title":"TensorFlow: A system for large-scale machine learning","author":"abadi","year":"2016","journal-title":"12th USENIX Symposium on OSDI"},{"doi-asserted-by":"publisher","key":"ref36","DOI":"10.1109\/SLT.2018.8639690"},{"doi-asserted-by":"publisher","key":"ref35","DOI":"10.1109\/ICASSP.2012.6289079"},{"doi-asserted-by":"publisher","key":"ref34","DOI":"10.1109\/ASRU46091.2019.9003913"},{"key":"ref10","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"doi-asserted-by":"publisher","key":"ref40","DOI":"10.1109\/ICASSP40776.2020.9054188"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.21437\/Interspeech.2020-3015"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1109\/ICASSP40776.2020.9053600"},{"year":"2020","author":"wang","article-title":"Attention-based transducer for online speech recognition","key":"ref13"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.21437\/Interspeech.2020-2361"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1109\/ICASSP39728.2021.9413803"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1109\/ICASSP40776.2020.9054715"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref18","first-page":"1081","article-title":"Effective sentence scoring method using BERT for speechrecognition","author":"shin","year":"2019","journal-title":"ACML"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.21437\/Interspeech.2021-313"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.21437\/Interspeech.2021-165"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.21437\/Interspeech.2020-3016"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1109\/SLT48900.2021.9383497"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/ICASSP39728.2021.9413535"},{"year":"2019","author":"yeh","article-title":"Transformer-transducer: End-to-end speech recognition with self-attention","key":"ref6"},{"doi-asserted-by":"publisher","key":"ref29","DOI":"10.1109\/ICASSP39728.2021.9413899"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/ICASSP40776.2020.9053896"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1109\/ICASSP39728.2021.9414716"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/SLT48900.2021.9383506"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/ICASSP39728.2021.9414607"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1162\/neco.1997.9.8.1735"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.21437\/Interspeech.2021-206"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1109\/ICASSP40776.2020.9053051"},{"year":"2017","author":"oord","article-title":"Parallel wavenet: Fast high-fidelity speech synthesis","key":"ref45"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.21437\/Interspeech.2018-1616"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1109\/ICASSP.2018.8462682"},{"year":"2013","author":"yu","article-title":"Feature learning in deep neural networks-studies on speech recognition tasks","key":"ref42"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.21437\/Interspeech.2020-2986"},{"doi-asserted-by":"publisher","key":"ref41","DOI":"10.21437\/Interspeech.2017-1510"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1109\/SLT48900.2021.9383560"},{"doi-asserted-by":"publisher","key":"ref44","DOI":"10.21437\/Interspeech.2019-1209"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1109\/ICASSP40776.2020.9053606"},{"doi-asserted-by":"publisher","key":"ref43","DOI":"10.21437\/Interspeech.2019-2680"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.1109\/SLT.2018.8639034"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2022,5,23]]},"location":"Singapore, Singapore","end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09746406.pdf?arnumber=9746406","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T20:12:26Z","timestamp":1661199146000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746406\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746406","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}