{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T16:24:33Z","timestamp":1778084673988,"version":"3.51.4"},"reference-count":32,"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\/icassp48485.2024.10447662","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"10001-10005","source":"Crossref","is-referenced-by-count":11,"title":["Communication-Efficient Personalized Federated Learning for Speech-to-Text Tasks"],"prefix":"10.1109","author":[{"given":"Yichao","family":"Du","sequence":"first","affiliation":[{"name":"University of Science and Technology of China,State Key Laboratory of Cognitive Intelligence"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhirui","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tencent AI Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Linan","family":"Yue","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,State Key Laboratory of Cognitive Intelligence"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xu","family":"Huang","sequence":"additional","affiliation":[{"name":"Nanjing University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuqing","family":"Zhang","sequence":"additional","affiliation":[{"name":"Anhui Xinhua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tong","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,State Key Laboratory of Cognitive Intelligence"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Linli","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,State Key Laboratory of Cognitive Intelligence"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Enhong","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,State Key Laboratory of Cognitive Intelligence"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1002\/9781118706664"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.1109\/ICASSP39728.2021.9413397","article-title":"Training speech recognition models with federated learning: A quality\/cost framework","volume-title":"ICASSP","author":"Guliani"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747161"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414305"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096426"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-803"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-252"},{"key":"ref8","doi-asserted-by":"crossref","DOI":"10.1109\/ICASSP39728.2021.9413453","article-title":"Decentralizing feature extraction with quantum convolutional neural network for automatic speech recognition","volume-title":"ICASSP","author":"Yang"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096983"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-720"},{"key":"ref11","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"AISTATS","author":"McMahan"},{"key":"ref12","article-title":"Attention is all you need","volume-title":"NIPS","author":"Vaswani"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21303"},{"key":"ref14","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"ICML","author":"Radford"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.iwslt-1.3"},{"key":"ref17","article-title":"Lora: Low-rank adaptation of large language models","volume-title":"ICLR","author":"Hu"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2027"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1965"},{"key":"ref20","article-title":"Generalization through memorization: Nearest neighbor language models","volume-title":"ICLR","author":"Khandelwal"},{"key":"ref21","article-title":"Nearest neighbor machine translation","volume-title":"ICLR","author":"Khandelwal"},{"key":"ref22","article-title":"Non-parametric on-line learning from human feedback for neural machine translation","volume-title":"AAAI","author":"Wang"},{"key":"ref23","article-title":"Personalized federated learning through local memorization","volume-title":"ICML","author":"Marfoq"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.21"},{"key":"ref25","article-title":"Improving few-shot performance of language models via nearest neighbor calibration","author":"Nie","year":"2022"},{"key":"ref26","article-title":"Federated nearest neighbor machine translation","volume-title":"ICLR","author":"Du"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.964"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-short.47"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.47"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.284"},{"key":"ref31","article-title":"Simple and scalable nearest neighbor machine translation","volume-title":"ICLR","author":"Dai"},{"key":"ref32","article-title":"Must-c: a multilingual speech translation corpus","volume-title":"NAACL","author":"Di Gangi"}],"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\/10447662.pdf?arnumber=10447662","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:55:55Z","timestamp":1722578155000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447662\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447662","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}