{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:17:15Z","timestamp":1776885435564,"version":"3.51.2"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096812","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":4,"title":["Investigation into Phone-Based Subword Units for Multilingual End-to-End Speech Recognition"],"prefix":"10.1109","author":[{"given":"Saierdaer","family":"Yusuyin","sequence":"first","affiliation":[{"name":"Xinjiang University,School of Information Science and Engineering,Urumqi,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Huang","sequence":"additional","affiliation":[{"name":"Xinjiang University,School of Information Science and Engineering,Urumqi,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junhua","family":"Liu","sequence":"additional","affiliation":[{"name":"iFlyTek,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cong","family":"Liu","sequence":"additional","affiliation":[{"name":"iFlyTek,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683531"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846248"},{"key":"ref23","article-title":"Gradient vaccine: Investigating and improving multi-task optimization in massively multilingual models","author":"wang","year":"2021","journal-title":"Proceedings of the International Conference on Learning Representations (ICLR)"},{"key":"ref15","first-page":"4218","article-title":"Common voice: A massively-multilingual speech corpus","author":"ardila","year":"2020","journal-title":"Proceedings of the Twelfth Language Resources and Evaluation Conference"},{"key":"ref14","article-title":"Cross-lingual language model pretraining","author":"conneau","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref11","first-page":"2095","article-title":"Transformer based grapheme-to-phoneme conversion","author":"sevinj","year":"2019","journal-title":"Proceedings of Interspeech 2019"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687871"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178767"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414379"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289079"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.58"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref8","author":"moran","year":"2019","journal-title":"PHOIBLE 2 0 Max Planck Institute for the Science of Human History"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639248"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683536"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1787"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"3705","DOI":"10.21437\/Interspeech.2020-2513","article-title":"That sounds familiar: an analysis of phonetic representations transfer across languages","author":"?elasko","year":"2020","journal-title":"Proceedings of INTERSPEECH 2020"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1873"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682494"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096812.pdf?arnumber=10096812","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:01:09Z","timestamp":1700506869000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096812\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096812","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}