{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:48:13Z","timestamp":1730231293756,"version":"3.28.0"},"reference-count":22,"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\/icassp49357.2023.10095966","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":["Modular Conformer Training for Flexible End-to-End ASR"],"prefix":"10.1109","author":[{"given":"Kartik","family":"Audhkhasi","sequence":"first","affiliation":[{"name":"Google LLC,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Brian","family":"Farris","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bhuvana","family":"Ramabhadran","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pedro J.","family":"Moreno","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"year":"2020","author":"yu","article-title":"Dual-mode ASR: Unify and improve streaming asr with full-context modeling","key":"ref13"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.21437\/Interspeech.2021-720"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.18653\/v1\/2021.emnlp-main.541"},{"key":"ref14","article-title":"Learning multiple visual domains with residual adapters","volume":"30","author":"rebuffi","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref20","first-page":"5206","article-title":"Librispeech: an ASR corpus based on public domain audio books","author":"panayotov","year":"2015","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"year":"2020","author":"tripathi","article-title":"Transformer transducer: One model unifying streaming and non-streaming speech recognition","key":"ref11"},{"year":"2020","author":"zhang","article-title":"Pushing the limits of semi-supervised learning for automatic speech recognition","key":"ref22"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.21437\/Interspeech.2022-10791"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"year":"2015","author":"chan","article-title":"Listen, attend and spell","key":"ref2"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1561\/116.00000050"},{"year":"2019","author":"fan","article-title":"Reducing transformer depth on demand with structured dropout","key":"ref17"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.21437\/Interspeech.2021-1884"},{"key":"ref19","first-page":"193","article-title":"Exploring architectures, data and units for streaming end-to-end speech recognition with RNN-transducer","author":"rao","year":"2017","journal-title":"Proc IEEE Workshop Automatic Speech Recognition and Understanding (ASRU)"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1109\/CVPR.2017.195"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1109\/ICASSP39728.2021.9414607"},{"key":"ref7","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/ICASSP43922.2022.9747879"},{"year":"1998","author":"jelinek","journal-title":"Statistical Methods for Speech Recognition","key":"ref4"},{"year":"2012","author":"graves","article-title":"Sequence transduction with recurrent neural networks","key":"ref3"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.21437\/Interspeech.2020-3015"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/MSP.2012.2205597"}],"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\/10095966.pdf?arnumber=10095966","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T13:57:38Z","timestamp":1699883858000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095966\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095966","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}