{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T08:06:54Z","timestamp":1768982814589,"version":"3.49.0"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9747161","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"7227-7231","source":"Crossref","is-referenced-by-count":26,"title":["End-to-End Speech Recognition from Federated Acoustic Models"],"prefix":"10.1109","author":[{"given":"Yan","family":"Gao","sequence":"first","affiliation":[{"name":"University of Cambridge"}]},{"given":"Titouan","family":"Parcollet","sequence":"additional","affiliation":[{"name":"Avignon University"}]},{"given":"Salah","family":"Zaiem","sequence":"additional","affiliation":[{"name":"Telecom Paris"}]},{"given":"Javier","family":"Fernandez-Marques","sequence":"additional","affiliation":[{"name":"University of Oxford"}]},{"given":"Pedro P. B.","family":"de Gusmao","sequence":"additional","affiliation":[{"name":"University of Cambridge"}]},{"given":"Daniel J.","family":"Beutel","sequence":"additional","affiliation":[{"name":"University of Cambridge"}]},{"given":"Nicholas D.","family":"Lane","sequence":"additional","affiliation":[{"name":"University of Cambridge"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853678"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3390\/e22111235"},{"key":"ref31","article-title":"A first look into the carbon footprint of federated learning","author":"qiu","year":"2021"},{"key":"ref30","article-title":"Fjord: Fair and accurate federated learning under heterogeneous targets with ordered dropout","author":"horvath","year":"2021"},{"key":"ref36","article-title":"Adaptive federated optimization","author":"reddi","year":"2020","journal-title":"arXiv preprint arXiv 2003 07516"},{"key":"ref35","article-title":"pyannote.audio: neural building blocks for speaker diarization","author":"bredin","year":"2019"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953194"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1791"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414305"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2944"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2039"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413397"},{"key":"ref15","article-title":"Federated learning with non-iid data","author":"zhao","year":"2018","journal-title":"arXiv preprint arXiv 1806 00582"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2944481"},{"key":"ref17","article-title":"Transformers with convolutional context for asr","author":"mohamed","year":"2019","journal-title":"arXiv preprint arXiv 1904 12848"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004025"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1006\/csla.2001.0184"},{"key":"ref28","article-title":"SpeechBrain: A general-purpose speech toolkit","author":"ravanelli","year":"2021"},{"key":"ref4","article-title":"Neural speech recognizer: Acoustic-to-word lstm model for large vocabulary speech recognition","author":"soltau","year":"2016","journal-title":"arXiv preprint arXiv 1610 09975"},{"key":"ref27","article-title":"Flower: A friendly federated learning research framework","author":"beutel","year":"2020","journal-title":"arXiv preprint arXiv 2007 14638"},{"key":"ref3","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in english and mandarin","author":"amodei","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref6","article-title":"Federated learning: Strategies for improving communication efficiency","author":"kone?n?","year":"2016","journal-title":"arXiv preprint arXiv 1610 05492"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.2975749"},{"key":"ref5","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","author":"mcmahan","year":"2017","journal-title":"Artificial Intelligence and Statistics"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3023"},{"key":"ref7","article-title":"Advances and open problems in federated learning","author":"kairouz","year":"2019","journal-title":"arXiv preprint arXiv 1912 04977"},{"key":"ref2","article-title":"Deep speech: Scaling up end-to-end speech recognition","author":"hannun","year":"2014","journal-title":"arXiv preprint arXiv 1412 5567"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683546"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICACCCN.2018.8748399"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"206","DOI":"10.1109\/ASRU.2017.8268937","article-title":"Exploring neural transducers for end-to-end speech recognition","author":"battenberg","year":"2017","journal-title":"Automatic Speech Recognition and Understanding (ASRU) 2017 IEEE Workshop on"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1006"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953164"},{"key":"ref26","article-title":"Common voice: A massively-multilingual speech corpus","author":"ardila","year":"2019","journal-title":"arXiv preprint arXiv 1912 06670"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09747161.pdf?arnumber=9747161","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:09:10Z","timestamp":1660594150000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747161\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747161","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}