{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T00:02:46Z","timestamp":1783641766704,"version":"3.55.0"},"reference-count":33,"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\/icassp48485.2024.10445894","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"6900-6904","source":"Crossref","is-referenced-by-count":6,"title":["A Comparison of Parameter-Efficient ASR Domain Adaptation Methods for Universal Speech and Language Models"],"prefix":"10.1109","author":[{"given":"Khe Chai","family":"Sim","sequence":"first","affiliation":[{"name":"Google,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhouyuan","family":"Huo","sequence":"additional","affiliation":[{"name":"Google,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tsendsuren","family":"Munkhdalai","sequence":"additional","affiliation":[{"name":"Google,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nikhil","family":"Siddhartha","sequence":"additional","affiliation":[{"name":"Google,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adam","family":"Stooke","sequence":"additional","affiliation":[{"name":"Google,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhong","family":"Meng","sequence":"additional","affiliation":[{"name":"Google,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Li","sequence":"additional","affiliation":[{"name":"Google,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tara","family":"Sainath","sequence":"additional","affiliation":[{"name":"Google,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021"},{"key":"ref2","article-title":"PaLM 2 technical report","author":"Anil","year":"2023"},{"key":"ref3","article-title":"GPT-4 technical report","year":"2023","journal-title":"OpenAI"},{"key":"ref4","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref5","article-title":"Google USM: Scaling automatic speech recognition beyond 100 languages","author":"Zhang","year":"2023"},{"key":"ref6","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref7","article-title":"Scaling speech technology to 1,000+ languages","author":"Pratap","year":"2023"},{"key":"ref8","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688253"},{"key":"ref10","article-title":"Self-supervised learning with random-projection quantizer for speech recognition","volume-title":"International Conference on Machine Learning","author":"Chiu"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11034"},{"key":"ref12","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"International Conference on Machine Learning","author":"Houlsby"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746719"},{"key":"ref14","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2601146"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2246"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096799"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096330"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3182537"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.1"},{"key":"ref23","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref24","article-title":"A survey for in-context learning","author":"Dong","year":"2022"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref26","article-title":"Spot: Better frozen model adaptation through soft prompt transfer","author":"Vu","year":"2021"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"ref28","article-title":"Learning multiple visual domains with residual adapters","volume":"30","author":"Rebuffi","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2215"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639610"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707758"},{"key":"ref32","article-title":"Artificial intelligence at google: Our principles"},{"key":"ref33","article-title":"Parameter-efficient fine-tuning design spaces","author":"Chen","year":"2023"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"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\/10445894.pdf?arnumber=10445894","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:37:30Z","timestamp":1722573450000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10445894\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10445894","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}