{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T15:18:07Z","timestamp":1725808687241},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447164","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"11806-11810","source":"Crossref","is-referenced-by-count":0,"title":["Task Oriented Dialogue as a Catalyst for Self-Supervised Automatic Speech Recognition"],"prefix":"10.1109","author":[{"given":"David M.","family":"Chan","sequence":"first","affiliation":[{"name":"University of California,Berkeley"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shalini","family":"Ghosh","sequence":"additional","affiliation":[{"name":"Amazon Alexa AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hitesh","family":"Tulsiani","sequence":"additional","affiliation":[{"name":"Amazon Alexa AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ariya","family":"Rastrow","sequence":"additional","affiliation":[{"name":"Amazon Alexa AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bj\u00f6rn","family":"Hoffmeister","sequence":"additional","affiliation":[{"name":"Amazon Alexa AI"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-022-1347-y"},{"article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"ICML","author":"Radford","key":"ref2"},{"key":"ref3","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"Baevski","year":"2020","journal-title":"NeurIPS"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414460"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746449"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094924"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-40498-6_25"},{"key":"ref8","article-title":"Recent advances in natural language processing via large pre-trained language models: A survey","author":"Min","year":"2021","journal-title":"ACM Computing Surveys"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095204"},{"article-title":"Spokenwoz: A large-scale speech-text benchmark for spoken task-oriented dialogue agents","year":"2023","author":"Si","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639044"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687895"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1434"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746126"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688079"},{"article-title":"Generative asr error correction with large language models","volume-title":"ASRU","author":"Yang","key":"ref16"},{"article-title":"Using external off-policy speech-to-text mappings in contextual end-to-end automated speech recognition","volume-title":"ICASSP","author":"Chan","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-10928-8_50"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-390"},{"article-title":"Supervised contrastive learning","year":"2021","author":"Khosla","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-5506"},{"key":"ref22","first-page":"5016","article-title":"MultiWOZ - a large-scale multi-domain Wizard-of-Oz dataset for task-oriented dialogue modelling","author":"Budzianowski","year":"2018"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.sigdial-1.28"},{"article-title":"Noesis ii: Predicting responses, identifying success, and managing complexity in task-oriented dialogue","volume-title":"AAAI: Workshop on Dialog System Tech Challenges","author":"Gunasekara","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.401"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-612"},{"article-title":"Nemo: a toolkit for building ai applications using neural modules","year":"2019","author":"Kuchaiev","key":"ref27"},{"article-title":"YourTTS: Towards zero-shot multi-speaker tts and zero-shot voice conversion for everyone","volume-title":"ICML","author":"Casanova","key":"ref28"},{"key":"ref29","first-page":"4218","article-title":"Common voice: A massively-multilingual speech corpus","author":"Ardila","year":"2020"},{"year":"2023","key":"ref30","article-title":"Introducing mpt-30b: Raising the bar for open-source foundation models"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4337"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/asru51503.2021.9688274"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126658"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383517"},{"article-title":"Bertscore: Evaluating text generation with bert","volume-title":"ICLR","author":"Zhang","key":"ref36"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10447164.pdf?arnumber=10447164","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:47:01Z","timestamp":1722574021000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447164\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447164","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}