{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T10:47:59Z","timestamp":1725706079420},"reference-count":29,"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\/icassp49357.2023.10095838","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["A Comparison of Semi-Supervised Learning Techniques for Streaming ASR at Scale"],"prefix":"10.1109","author":[{"given":"Cal","family":"Peyser","sequence":"first","affiliation":[{"name":"New York University,Center for Data Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Picheny","sequence":"additional","affiliation":[{"name":"New York University,Center for Data Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kyunghyun","family":"Cho","sequence":"additional","affiliation":[{"name":"New York University,Center for Data Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rohit","family":"Prabhavalkar","sequence":"additional","affiliation":[{"name":"Google Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"W. Ronny","family":"Huang","sequence":"additional","affiliation":[{"name":"Google Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tara N.","family":"Sainath","sequence":"additional","affiliation":[{"name":"Google Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1109\/ASRU51503.2021.9688018"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1145\/3394486.3403331"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.21437\/Interspeech.2019-3167"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1109\/ICASSP.2019.8683307"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1109\/ICASSP40776.2020.9053600"},{"key":"ref10","article-title":"Cold fusion: Training seq2seq models together with language models","author":"sriram","year":"2017","journal-title":"CoRR"},{"key":"ref2","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"2012","journal-title":"International Conference on Machine Learning (ICML)"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref17","article-title":"SLAM: A unified encoder for speech and language modeling via speech-text joint pre-training","author":"bapna","year":"2021","journal-title":"Annual Meeting of the Association for Computational Linguistics (ACL)"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1109\/ICASSP43922.2022.9746554"},{"key":"ref19","article-title":"Joist: A joint speech and text streaming model for asr","author":"sainath","year":"2022","journal-title":"Proc IEEE\/ACL Workshop Spoken Lang Technol (SLT)"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.18653\/v1\/2022.acl-long.105"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref23","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020","journal-title":"CoRR"},{"key":"ref26","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","author":"baevski","year":"2019","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref25","article-title":"Wavlm: Large-scale self-supervised pre-training for full stack speech processing","author":"chen","year":"2021","journal-title":"CoRR"},{"key":"ref20","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"CoRR"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.21437\/Interspeech.2019-1873"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1109\/JSTSP.2022.3207050"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1109\/ICASSP39728.2021.9414607"},{"key":"ref27","article-title":"Self-supervised learning with random-projection quantizer for speech recognition","author":"chiu","year":"2022","journal-title":"International Conference on Machine Learning (ICML)"},{"doi-asserted-by":"publisher","key":"ref29","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref8","article-title":"Joint unsupervised and supervised training for multilingual ASR","author":"bai","year":"2021","journal-title":"International Conference on Acoustics Speech Signal Processing (ICASSP)"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref9","article-title":"On using monolingual corpora in neural machine translation","author":"g\u00fcl\u00e7ehre","year":"2015","journal-title":"CoRR"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.21437\/Interspeech.2020-2947"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref6","article-title":"Deep unsupervised learning from speech","author":"drexler","year":"2016","journal-title":"Ph D thesis"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/ICASSP.2013.6638959"}],"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\/10095838.pdf?arnumber=10095838","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:11:09Z","timestamp":1700507469000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095838\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095838","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}