{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T10:57:13Z","timestamp":1730199433661,"version":"3.28.0"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"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":[[2023,12,16]]},"DOI":"10.1109\/asru57964.2023.10389744","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T18:38:40Z","timestamp":1705689520000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Audio-Adapterfusion: A Task-Id-Free Approach for Efficient and Non-Destructive Multi-Task Speech Recognition"],"prefix":"10.1109","author":[{"given":"Hillary","family":"Ngai","sequence":"first","affiliation":[{"name":"Google LLC"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rohan","family":"Agrawal","sequence":"additional","affiliation":[{"name":"Google LLC"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Neeraj","family":"Gaur","sequence":"additional","affiliation":[{"name":"Google LLC"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ronny","family":"Huang","sequence":"additional","affiliation":[{"name":"Google LLC"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Parisa","family":"Haghani","sequence":"additional","affiliation":[{"name":"Google LLC"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pedro Moreno","family":"Mengibar","sequence":"additional","affiliation":[{"name":"Google LLC"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-2620"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref3","article-title":"Pushing the limits of semi-supervised learning for automatic speech recognition","author":"Zhang","year":"2020","journal-title":"arXiv preprint arXiv:2010.10504"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2022.10.001"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414858"},{"key":"ref6","article-title":"An experimental evaluation of transformer-based language models in the biomedical domain","volume":"abs\/2012.15419","author":"Grouchy","year":"2020","journal-title":"CoRR"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746223"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2017.7953075"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415058"},{"key":"ref10","article-title":"Sentence encoders on stilts: Supplementary training on intermediate labeled-data tasks","author":"Phang","year":"2018","journal-title":"arXiv preprint arXiv:1811.01088"},{"key":"ref11","article-title":"Transformer-based models for question answering on covid19","author":"Ngai","year":"2021","journal-title":"arXiv preprint arXiv:2101.11432"},{"article-title":"Effect of scale on catastrophic forgetting in neural networks","volume-title":"International Conference on Learning Representations","author":"Ramasesh","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref14","article-title":"An overview of multi-task learning in deep neural networks","author":"Ruder","year":"2017","journal-title":"arXiv preprint arXiv:1706.05098"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414379"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2943604"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1495"},{"key":"ref18","first-page":"18878","article-title":"Conflict-averse gradient descent for multi-task learning","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Liu"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.bionlp-1.33"},{"key":"ref20","first-page":"2790","article-title":"Parameter-efficient transfer learning for nlp","volume-title":"International Conference on Machine Learning","author":"Houlsby"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3138674"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10095837"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2215"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.39"},{"key":"ref25","article-title":"Layer normalization","author":"Ba","year":"2016","journal-title":"arXiv preprint arXiv:1607.06450"},{"key":"ref26","article-title":"Sequence transduction with recurrent neural networks","author":"Graves","year":"2012","journal-title":"arXiv preprint arXiv:1211.3711"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21105\/joss.00753"},{"key":"ref28","first-page":"5986","article-title":"Bert and pals: Projected attention layers for efficient adaptation in multi-task learning","volume-title":"International Conference on Machine Learning","author":"Stickland"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053600"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413803"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095838"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2680"}],"event":{"name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","start":{"date-parts":[[2023,12,16]]},"location":"Taipei, Taiwan","end":{"date-parts":[[2023,12,20]]}},"container-title":["2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10388490\/10389614\/10389744.pdf?arnumber=10389744","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T16:42:41Z","timestamp":1706028161000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10389744\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,16]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/asru57964.2023.10389744","relation":{},"subject":[],"published":{"date-parts":[[2023,12,16]]}}}