{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:45:02Z","timestamp":1730231102106,"version":"3.28.0"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10095464","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T13:28:30Z","timestamp":1683293310000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Lego-Features: Exporting Modular Encoder Features for Streaming and Deliberation ASR"],"prefix":"10.1109","author":[{"given":"Rami","family":"Botros","sequence":"first","affiliation":[{"name":"Google LLC,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rohit","family":"Prabhavalkar","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Johan","family":"Schalkwyk","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ciprian","family":"Chelba","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tara N.","family":"Sainath","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fran\u00e7oise","family":"Beaufays","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Enforcing encoder-decoder modularity in sequence-to-sequence models","author":"dalmia","year":"2019","journal-title":"arXiv preprint arXiv 1911 13084"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref12","article-title":"Pre-training on high-resource speech recognition improves low-resource speech-to-text translation","author":"bansal","year":"2018","journal-title":"arXiv preprint arXiv 1809 01431"},{"key":"ref34","article-title":"Improving Wideband Speech Rcognition using Mixed-bandwidth Training Data in CD-DNN-HMM","author":"li","year":"2012","journal-title":"Proc SLT"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053606"},{"key":"ref37","article-title":"Ctc alignments improve autoregressive translation","author":"yan","year":"2022","journal-title":"arXiv preprint arXiv 2210 05200"},{"key":"ref14","article-title":"Legonn: Building modular encoder-decoder models","author":"dalmia","year":"2022","journal-title":"arXiv 2206 03318"},{"article-title":"The label bias problem","year":"2020","author":"hannun","key":"ref36"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707758"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11034"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052937"},{"key":"ref33","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1510","article-title":"Generation of Large-Scale Simulated Utterances in Virtual Rooms to Train Deep-Neural Networks for Far-Field Speech Recognition in Google Home","author":"kim","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-233"},{"year":"0","key":"ref32","article-title":"Google ai principles"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413899"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-275"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.16932"},{"key":"ref16","article-title":"Relative representations enable zero-shot latent space communication","author":"moschella","year":"2022","journal-title":"arXiv preprint arXiv 2209 15430"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746390"},{"key":"ref18","article-title":"Align-refine: Non-autoregressive speech recognition via iterative realignment","author":"chi","year":"2020","journal-title":"arXiv preprint arXiv 2010 14318"},{"key":"ref24","article-title":"Sequence Transduction with Recurrent Neural Networks","volume":"abs 1211 3711","author":"graves","year":"2012","journal-title":"CoRR"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003913"},{"key":"ref25","article-title":"Listen, attend and spell","volume":"abs 1508 1211","author":"chan","year":"2015","journal-title":"CoRR"},{"key":"ref20","article-title":"Streaming align-refine for non-autoregressive deliberation","author":"wang","year":"2022","journal-title":"arXiv preprint arXiv 2204 07556"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747879"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-212"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289079"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054188"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-206"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1855"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054188"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682336"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003906"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10095464.pdf?arnumber=10095464","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T13:57:06Z","timestamp":1700488626000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095464\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095464","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}