{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,19]],"date-time":"2025-04-19T04:53:00Z","timestamp":1745038380577,"version":"3.28.0"},"reference-count":55,"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\/icassp49357.2023.10096330","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":9,"title":["Efficient Domain Adaptation for Speech Foundation Models"],"prefix":"10.1109","author":[{"given":"Bo","family":"Li","sequence":"first","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Dongseong","family":"Hwang","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Zhouyuan","family":"Huo","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Junwen","family":"Bai","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Guru","family":"Prakash","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Tara N.","family":"Sainath","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Khe","family":"Chai Sim","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Yu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Wei","family":"Han","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Trevor","family":"Strohman","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Francoise","family":"Beaufays","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]}],"member":"263","reference":[{"key":"ref1","article-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021","journal-title":"arXiv:2108.07258"},{"key":"ref2","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. NeurIPS","volume":"33","author":"Brown"},{"key":"ref3","article-title":"Towards a human-like open-domain chatbot","author":"Adiwardana","year":"2020","journal-title":"arXiv:2001.09977"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639610"},{"key":"ref5","article-title":"Speechstew: Simply mix all available speech recognition data to train one large neural network","author":"Chan","year":"2021","journal-title":"arXiv:2104.02133"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1965"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3182537"},{"key":"ref8","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Tech. Rep., Technical report, OpenAI, 2022","author":"Radford","year":"2022"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11034"},{"key":"ref10","article-title":"ESB: A Benchmark For Multi-Domain End-to-End Speech Recognition","author":"Gandhi","year":"2022","journal-title":"arXiv:2210.13352"},{"key":"ref11","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. NeurIPS","author":"Baevski","key":"ref12"},{"issue":"140","key":"ref13","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res"},{"key":"ref14","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv:1807.03748"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2938863"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746430"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747357"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639610"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687871"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746594"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707758"},{"key":"ref22","article-title":"YouTube by the Numbers"},{"key":"ref23","first-page":"2790","article-title":"Parameter-efficient transfer learning for nlp","volume-title":"Proc. ICML. PMLR","author":"Houlsby"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746719"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10613"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.7"},{"key":"ref27","article-title":"Towards a unified view of parameter-efficient transfer learning","author":"He","year":"2021","journal-title":"arXiv:2110.04366"},{"article-title":"Voice2series: Reprogramming acoustic models for time series classification","volume-title":"Proc. ICML. PMLR","author":"Yang","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688253"},{"key":"ref30","article-title":"Self-supervised learning with random-projection quantizer for speech recognition","author":"Chiu","year":"2022","journal-title":"arXiv:2202.01855"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref32","article-title":"Listen, attend and spell","volume":"abs\/1508.01211","author":"Chan","year":"2015","journal-title":"CoRR"},{"key":"ref33","article-title":"Sequence Transduction with Recurrent Neural Networks","volume":"abs\/1211.3711","author":"Graves","year":"2012","journal-title":"CoRR"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003913"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747390"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746038"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1470"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01070"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1203"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639038"},{"key":"ref41","article-title":"SLAM: A unified encoder for speech and language modeling via speech-text joint pre-training","author":"Bapna","year":"2021","journal-title":"arXiv:2110.10329"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10937"},{"journal-title":"arXiv:2210.07353","article-title":"JOIST: A Joint Speech and Text Streaming Model For ASR","year":"2022","key":"ref43"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2908700"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383518"},{"key":"ref46","article-title":"Artificial Intelligence at Google: Our Principles"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2416"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref50","article-title":"Lingvo: a modular and scalable framework for sequence-to-sequence modeling","author":"Shen","year":"2019","journal-title":"arXiv:2005.08100"},{"key":"ref51","article-title":"Cloud Tensor Processing Units (TPUs"},{"key":"ref52","first-page":"4596","article-title":"Adafactor: Adaptive learning rates with sublinear memory cost","volume-title":"Proc. ICML. PMLR","author":"Shazeer"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003854"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1566"}],"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\/10096330.pdf?arnumber=10096330","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,12]],"date-time":"2024-04-12T06:32:02Z","timestamp":1712903522000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096330\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096330","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}