{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,10]],"date-time":"2025-04-10T09:07:23Z","timestamp":1744276043002,"version":"3.28.0"},"reference-count":27,"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\/icassp49357.2023.10096799","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":3,"title":["Resource-Efficient Transfer Learning from Speech Foundation Model Using Hierarchical Feature Fusion"],"prefix":"10.1109","author":[{"given":"Zhouyuan","family":"Huo","sequence":"first","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Khe Chai","family":"Sim","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Bo","family":"Li","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Dongseong","family":"Hwang","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Tara N.","family":"Sainath","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Trevor","family":"Strohman","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]}],"member":"263","reference":[{"key":"ref13","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020","journal-title":"arXiv preprint arXiv 2006 11116"},{"key":"ref12","article-title":"Incremental layer-wise self-supervised learning for efficient speech domain adaptation on device","author":"huo","year":"2021","journal-title":"arXiv preprint arXiv 2110 07058"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688253"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref10","article-title":"Representation learning with contrastive predictive coding","author":"oord","year":"2018","journal-title":"arXiv preprint arXiv 1807 03748"},{"key":"ref2","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref1","article-title":"On the opportunities and risks of foundation models","author":"bommasani","year":"2021","journal-title":"arXiv preprint arXiv 2108 03490"},{"key":"ref17","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"arXiv preprint arXiv 1810 04805"},{"key":"ref16","article-title":"Self-supervised learning with random-projection quantizer for speech recognition","author":"chiu","year":"2022","journal-title":"arXiv preprint arXiv 2202 01855"},{"key":"ref19","first-page":"1022","article-title":"Compacter: Efficient low-rank hypercomplex adapter layers","volume":"34","author":"karimi mahabadi","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref18","first-page":"2790","article-title":"Parameter-efficient transfer learning for nlp","author":"houlsby","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"year":"0","key":"ref26","article-title":"Artificial intelligence at google: Our principles"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639610"},{"key":"ref20","article-title":"Lora: Low-rank adaptation of large language models","author":"hu","year":"2021","journal-title":"arXiv preprint arXiv 2106 09129"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11376"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688093"},{"key":"ref27","article-title":"Bitfit: Simple parameter-efficient fine-tuning for transformer-based masked language-models","author":"zaken","year":"2021","journal-title":"arXiv preprint arXiv 2106 10155"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054438"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746719"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053541"},{"key":"ref4","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":"ref3","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"radford","year":"2021","journal-title":"International Conference on Machine Learning"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3182537"},{"key":"ref5","article-title":"Roberta: A robustly optimized bert pretraining approach","author":"liu","year":"2019","journal-title":"arXiv preprint arXiv 1907 11634"}],"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\/10096799.pdf?arnumber=10096799","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T14:09:59Z","timestamp":1700489399000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096799\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096799","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}