{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:22:22Z","timestamp":1775229742827,"version":"3.50.1"},"reference-count":25,"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\/icassp48485.2024.10447004","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"11751-11755","source":"Crossref","is-referenced-by-count":16,"title":["Sparsely Shared Lora on Whisper for Child Speech Recognition"],"prefix":"10.1109","author":[{"given":"Wei","family":"Liu","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong,Department of Electronic Engineering"}]},{"given":"Ying","family":"Qin","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Beijing Jiaotong University,Beijing,China,100044"}]},{"given":"Zhiyuan","family":"Peng","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Department of Electronic Engineering"}]},{"given":"Tan","family":"Lee","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Department of Electronic Engineering"}]}],"member":"263","reference":[{"key":"ref1","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":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-143"},{"key":"ref3","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref4","article-title":"Google USM: Scaling automatic speech recognition beyond 100 languages","author":"Zhang","year":"2023"},{"key":"ref5","article-title":"Scaling speech technology to 1,000+ languages","author":"Pratap","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101289"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413634"},{"key":"ref8","article-title":"Applying wav2vec2. 0 to speech recognition in various low-resource languages","author":"Yi","year":"2020"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-tutorials.5"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00626-4"},{"key":"ref11","article-title":"Towards a unified view of parameter-efficient transfer learning","volume-title":"Proc. of ICLR","author":"He"},{"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":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"ref15","article-title":"Lora: Low-rank adaptation of large language models","volume-title":"Proc. of ICLR","author":"Hu"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.1"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-short.107"},{"key":"ref18","article-title":"One-for-all: Generalized lora for parameter-efficient fine-tuning","author":"Chavan","year":"2023"},{"key":"ref19","first-page":"1950","article-title":"Few-shot parameter-efficient fine-tuning is better and cheaper than in-context learning","volume":"35","author":"Liu","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.568"},{"key":"ref22","first-page":"26809","article-title":"Platon: Pruning large transformer models with upper confidence bound of weight importance","volume-title":"International Conference on Machine Learning","author":"Zhang"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383608"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"ref25","first-page":"4218","article-title":"Common voice: A massively-multilingual speech corpus","volume-title":"Proc. of LREC","author":"Ardila"}],"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\/10447004.pdf?arnumber=10447004","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:28:41Z","timestamp":1722576521000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447004\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447004","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}