{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T08:02:19Z","timestamp":1764403339904},"reference-count":23,"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\/icassp48485.2024.10447116","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"12356-12360","source":"Crossref","is-referenced-by-count":2,"title":["Improving Speech Recognition for African American English with Audio Classification"],"prefix":"10.1109","author":[{"given":"Shefali","family":"Garg","sequence":"first","affiliation":[{"name":"Google LLC"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhouyuan","family":"Huo","sequence":"additional","affiliation":[{"name":"Google LLC"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Khe Chai","family":"Sim","sequence":"additional","affiliation":[{"name":"Google LLC"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Suzan","family":"Schwartz","sequence":"additional","affiliation":[{"name":"Google LLC"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mason","family":"Chua","sequence":"additional","affiliation":[{"name":"Google LLC"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Al\u00ebna","family":"Aks\u00ebnova","sequence":"additional","affiliation":[{"name":"Google LLC"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tsendsuren","family":"Munkhdalai","sequence":"additional","affiliation":[{"name":"Google LLC"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Levi","family":"King","sequence":"additional","affiliation":[{"name":"Google LLC"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Darryl","family":"Wright","sequence":"additional","affiliation":[{"name":"Google LLC"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zion","family":"Mengesha","sequence":"additional","affiliation":[{"name":"Google LLC"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongseong","family":"Hwang","sequence":"additional","affiliation":[{"name":"Google LLC"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tara","family":"Sainath","sequence":"additional","affiliation":[{"name":"Google LLC"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fran\u00e7oise","family":"Beaufays","sequence":"additional","affiliation":[{"name":"Google LLC"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pedro Moreno","family":"Mengibar","sequence":"additional","affiliation":[{"name":"Google LLC"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"6328","article-title":"Language technology practitioners as language managers: Arbitrating data bias and predictive bias in asr","volume-title":"Proceedings of the Thirteenth Language Resources and Evaluation Conference","author":"Markl"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.2196\/36388"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.126"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1915768117"},{"key":"ref5","first-page":"arXiv:2112.12572","article-title":"Are E2E ASR models ready for an industrial usage?","author":"Vielzeuf","year":"2021","journal-title":"arXiv e-prints"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053751"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10816"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2021.725911"},{"journal-title":"eWAVE","year":"2020","author":"Kortmann","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003913"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096330"},{"key":"ref12","article-title":"Searching for activation functions","author":"Ramachandran","year":"2017","journal-title":"CoRR"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref14","first-page":"3915","article-title":"Self-supervised learning with random-projection quantizer for speech recognition","volume-title":"International Conference on Machine Learning","author":"Chiu"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctv1g4rvf6.8"},{"key":"ref16","first-page":"4211","article-title":"Common Voice: A Massively-Multilingual Speech Corpus","volume-title":"Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020)","author":"Ardila"},{"key":"ref17","first-page":"3744","article-title":"Set transformer: A framework for attention-based permutation-invariant neural networks","volume-title":"International conference on machine learning","author":"Lee"},{"key":"ref18","article-title":"Accented speech recognition: Benchmarking, pre-training, and diverse data","author":"Aksenova","year":"2022","journal-title":"ArXiv"},{"volume-title":"American English: Dialects and Variation","year":"2015","author":"Wolfram","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053600"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413899"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289079"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11093"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","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\/10447116.pdf?arnumber=10447116","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:29:55Z","timestamp":1722576595000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447116\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447116","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}