{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:32:37Z","timestamp":1776889957142,"version":"3.51.2"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"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":[[2024,12,2]]},"DOI":"10.1109\/slt61566.2024.10832233","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:27Z","timestamp":1737052287000},"page":"468-475","source":"Crossref","is-referenced-by-count":2,"title":["Romanization Encoding For Multilingual ASR"],"prefix":"10.1109","author":[{"given":"Wen","family":"Ding","sequence":"first","affiliation":[{"name":"NVIDIA Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Jia","sequence":"additional","affiliation":[{"name":"NVIDIA Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hainan","family":"Xu","sequence":"additional","affiliation":[{"name":"NVIDIA Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Xi","sequence":"additional","affiliation":[{"name":"NVIDIA Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junjie","family":"Lai","sequence":"additional","affiliation":[{"name":"NVIDIA Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Boris","family":"Ginsburg","sequence":"additional","affiliation":[{"name":"NVIDIA Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2023","journal-title":"ICML"},{"key":"ref2","article-title":"Google usm: Scaling automatic speech recognition beyond 100 languages","author":"Zhang","year":"2023","journal-title":"arXiv preprint arXiv preprint arXiv:2303.01037"},{"key":"ref3","article-title":"Scaling speech technology to 1,000+ languages","author":"Pratap","year":"2023","journal-title":"arXiv preprint arXiv:2303.01037"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2032"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004035"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2277"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1007"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2440"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-04221-9_19"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1314"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094667"},{"key":"ref12","article-title":"Language models are unsupervised multitask learners","author":"Radford"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747842"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00560"},{"key":"ref15","article-title":"On the effectiveness of pinyin-character dual-decoding for end-to-end mandarin chinese asr","author":"Yang","year":"2022","journal-title":"arXiv preprint arXiv:2201.10792"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688053"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/asru51503.2021.9688174"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-4003"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.538"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/w19-1403"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2488"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2485"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2019.8682850"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095878"},{"key":"ref25","first-page":"5859","article-title":"Transformer-transducers for codeswitched speech recognition","author":"Dalmia","year":"2021","journal-title":"ICASSP"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053775"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K19-1026"},{"key":"ref28","first-page":"1057","article-title":"Improving CodeSwitching Language Modeling with Artificially Generated Texts Using Cycle-Consistent Adversarial Networks","volume-title":"Proc. Interspeech","author":"Li"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-563"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389701"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1211.3711"},{"key":"ref32","first-page":"38462","article-title":"Efficient sequence transduction by jointly predicting tokens and durations","author":"Xu","year":"2023","journal-title":"ICML"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-10340"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.calcs-1.7"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref36","article-title":"Aishell-2: Transforming mandarin asr research into industrial scale","author":"Du","year":"2018","journal-title":"arXiv preprint arXiv:1808.10583"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1429"},{"key":"ref38","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2015","journal-title":"ICLR"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"ref41","article-title":"Reazonspeech: A free and massive corpus for japanese asr","author":"Yin"}],"event":{"name":"2024 IEEE Spoken Language Technology Workshop (SLT)","location":"Macao","start":{"date-parts":[[2024,12,2]]},"end":{"date-parts":[[2024,12,5]]}},"container-title":["2024 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10830790\/10830793\/10832233.pdf?arnumber=10832233","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T08:14:54Z","timestamp":1737101694000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832233\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/slt61566.2024.10832233","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]}}}