{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T15:20:20Z","timestamp":1725808820995},"reference-count":38,"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\/icassp48485.2024.10447399","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"10841-10845","source":"Crossref","is-referenced-by-count":0,"title":["Efficient Adapter Finetuning for Tail Languages in Streaming Multilingual ASR"],"prefix":"10.1109","author":[{"given":"Junwen","family":"Bai","sequence":"first","affiliation":[{"name":"Google,USA"}]},{"given":"Bo","family":"Li","sequence":"additional","affiliation":[{"name":"Google,USA"}]},{"given":"Qiujia","family":"Li","sequence":"additional","affiliation":[{"name":"Google,USA"}]},{"given":"Tara N.","family":"Sainath","sequence":"additional","affiliation":[{"name":"Google,USA"}]},{"given":"Trevor","family":"Strohman","sequence":"additional","affiliation":[{"name":"Google,USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2831"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687871"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-143"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746594"},{"article-title":"Google USM: Scaling automatic speech recognition beyond 100 languages","year":"2023","author":"Zhang","key":"ref5"},{"article-title":"Scaling speech technology to 1,000+ languages","year":"2023","author":"Pratap","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096330"},{"year":"2023","key":"ref8","article-title":"GPT-4 technical report"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746038"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747879"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413899"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023346"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10006"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003870"},{"article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. ICML","author":"Houlsby","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3138674"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2215"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01070"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1470"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414959"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1390"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2858"},{"article-title":"mSLAM: Massively multilingual joint pre-training for speech and text","year":"2022","author":"Bapna","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i16.17661"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389760"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-480"},{"article-title":"Layer normalization","year":"2016","author":"Ba","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-57959-7"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"article-title":"Lingvo: a modular and scalable framework for sequence-to-sequence modeling","year":"2019","author":"Shen","key":"ref31"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3360307"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053600"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413803"},{"article-title":"Adam: A method for stochastic optimization","year":"2014","author":"Kingma","key":"ref36"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-329"}],"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\/10447399.pdf?arnumber=10447399","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:37:29Z","timestamp":1722577049000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447399\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447399","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}