{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,26]],"date-time":"2026-04-26T22:50:50Z","timestamp":1777243850270,"version":"3.51.4"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"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":[[2023,12,16]]},"DOI":"10.1109\/asru57964.2023.10389756","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T18:38:40Z","timestamp":1705689520000},"page":"1-8","source":"Crossref","is-referenced-by-count":11,"title":["Exploring Data Augmentation in Bias Mitigation Against Non-Native-Accented Speech"],"prefix":"10.1109","author":[{"given":"Yuanyuan","family":"Zhang","sequence":"first","affiliation":[{"name":"Delft University of Technology,Multimedia Computing Group,the Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aaricia","family":"Herygers","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tanvina","family":"Patel","sequence":"additional","affiliation":[{"name":"Delft University of Technology,Multimedia Computing Group,the Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengjun","family":"Yue","sequence":"additional","affiliation":[{"name":"Delft University of Technology,Multimedia Computing Group,the Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Odette","family":"Scharenborg","sequence":"additional","affiliation":[{"name":"Delft University of Technology,Multimedia Computing Group,the Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Inclusive speech technology","author":"Scharenborg"},{"key":"ref2","article-title":"Quantifying bias in automatic speech recognition","author":"Feng","year":"2021","journal-title":"arXiv preprint arXiv:2103.15122"},{"key":"ref3","article-title":"Using data augmentations and vtln to reduce bias in dutch end-to-end speech recognition systems","author":"Patel","year":"2023","journal-title":"arXiv preprint arXiv:2307.02009"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747654"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10816"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-1606"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3347449.3357480"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.gebnlp-1.10"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/S4SG.2022-4"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-836"},{"key":"ref11","article-title":"Automatic speech recognition of non-native child speech for language learning applications","volume-title":"12th Symposium on Languages, Applications and Technologies (SLATE)","author":"Wills"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-35292-8_15"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2015.09.272"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053334"},{"key":"ref15","article-title":"The effects of speakers\u2019 gender, age, and region on overall performance of arabic automatic speech recognition systems using the phonetically rich and balanced modern standard arabic speech corpus","volume-title":"Proceedings of the 2nd Workshop of Arabic Corpus Linguistics WACL-2","author":"Sawalha"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-21707-4_30"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1915768117"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.42"},{"key":"ref19","article-title":"Data augmentation for children\u2019s speech recognition\u2013the\u201d ethiopian\u201d system for the slt 2021 children speech recognition challenge","author":"Chen","year":"2020","journal-title":"arXiv preprint arXiv:2011.04547"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCCN.2008.ECP.157"},{"key":"ref21","article-title":"Wav2letter: an end-to-end convnet-based speech recognition system","author":"Collobert","year":"2016","journal-title":"arXiv preprint, arXiv:1609.03193"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-659"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414257"},{"issue":"1","key":"ref24","first-page":"2096","article-title":"Domain-adversarial training of neural networks","volume":"17","author":"Ganin","year":"2016","journal-title":"The journal of machine learning research"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1211"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2680"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2015-711"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2021.10.001"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-190"},{"key":"ref30","first-page":"158","article-title":"Bias in Flemish automatic speech recognition","author":"Herygers","year":"2023","journal-title":"Studientexte zur Sprachkommunikation: Elektronische Sprachsignalverarbeitung"},{"key":"ref31","article-title":"CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit (version 0.92)","author":"Junichi","year":"2019","journal-title":"University of Edinburgh. The Centre for Speech Technology Research (CSTR)"},{"key":"ref32","article-title":"The Spoken Dutch Corpus. Overview and first evaluation","volume-title":"Proc. 2nd International Conference on Language Resources and Evaluation (LREC\u201900)","author":"Oostdijk"},{"key":"ref33","article-title":"JASMIN-CGN: Extension of the Spoken Dutch Corpus with speech of elderly people, children and non-natives in the human-machine interaction modality","volume-title":"Proc. 5th International Conference on Language Resources and Evaluation (LREC\u201906)","author":"Cucchiarini"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2017.7953075"},{"key":"ref38","first-page":"27","article-title":"A hybrid asr system for southern dutch","volume":"11","author":"Van Dyck","year":"2021","journal-title":"Computational Linguistics in the Netherlands Journal"}],"event":{"name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Taipei, Taiwan","start":{"date-parts":[[2023,12,16]]},"end":{"date-parts":[[2023,12,20]]}},"container-title":["2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10388490\/10389614\/10389756.pdf?arnumber=10389756","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T16:21:12Z","timestamp":1706026872000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10389756\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,16]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/asru57964.2023.10389756","relation":{},"subject":[],"published":{"date-parts":[[2023,12,16]]}}}