{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T07:12:05Z","timestamp":1775200325867,"version":"3.50.1"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004164","name":"MediaTek","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004164","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,6]]},"DOI":"10.1109\/asru65441.2025.11434800","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["A Self-Refining Framework for Enhancing ASR Using TTS-Synthesized Data"],"prefix":"10.1109","author":[{"given":"Cheng-Kang","family":"Chou","sequence":"first","affiliation":[{"name":"MediaTek Research"}]},{"given":"Chan-Jan","family":"Hsu","sequence":"additional","affiliation":[{"name":"MediaTek Research"}]},{"given":"Ho-Lam","family":"Chung","sequence":"additional","affiliation":[{"name":"National Taiwan University"}]},{"given":"Liang-Hsuan","family":"Tseng","sequence":"additional","affiliation":[{"name":"National Taiwan University"}]},{"given":"Hsi-Chun","family":"Cheng","sequence":"additional","affiliation":[{"name":"National Taiwan University"}]},{"given":"Yu-Kuan","family":"Fu","sequence":"additional","affiliation":[{"name":"Nvidia"}]},{"given":"Kuan Po","family":"Huang","sequence":"additional","affiliation":[{"name":"National Taiwan University"}]},{"given":"Hung-Yi","family":"Lee","sequence":"additional","affiliation":[{"name":"National Taiwan University"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Canary-1b","year":"2023"},{"key":"ref2","article-title":"Robust speech recognition via largescale weak supervision","author":"Radford","year":"2022"},{"key":"ref3","article-title":"Phi-4-mini technical report: Compact yet powerful multimodal language and multimodal models","volume-title":"arXiv preprint arXiv:2503.01743","year":"2024"},{"key":"ref4","article-title":"Usm: Scaling automatic speech recognition beyond 100 languages","author":"Zhang","year":"2023","journal-title":"arXiv preprint arXiv:2303.01037"},{"key":"ref5","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint arXiv:2302.13971"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.841"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414778"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-906"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096971"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447240"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.503"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10889894"},{"key":"ref13","article-title":"Coqui tts","author":"G\u00edlge"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448291"},{"key":"ref15","article-title":"Cosyvoice: A scalable multilingual zero-shot text-to-speech synthesizer based on supervised semantic tokens","author":"Du","year":"2024","journal-title":"arXiv preprint arXiv:2407.05407"},{"key":"ref16","article-title":"Breezyvoice: Adapting tts for taiwanese mandarin with enhanced polyphone disambiguation-challenges and insights","author":"Hsu","year":"2025","journal-title":"arXiv preprint arXiv:2501.17790"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832290"},{"key":"ref18","article-title":"Whispering in amharic: Fine-tuning whisper for low-resource language","author":"Gete","year":"2025","journal-title":"arXiv preprint arXiv:2503.18485"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-907"},{"key":"ref20","article-title":"Improving the inclusivity of dutch speech recognition by fine-tuning whisper on the jasmin-cgn corpus","author":"Shekoufandeh","year":"2025","journal-title":"arXiv preprint arXiv:2502.17284"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/iceccme64568.2025.11277459"},{"key":"ref22","article-title":"Efficient adaptation of multilingual models for japanese ass","author":"Bajo","year":"2024","journal-title":"arXiv preprint arXiv:2412.10705"},{"key":"ref23","article-title":"Fine-tuning whisper on low-resource languages for real-world applications","author":"Timmel","year":"2024","journal-title":"arXiv preprint arXiv:2412.15726"},{"key":"ref24","first-page":"397","article-title":"The NTNU ASR system for Formosa speech recognition challenge 2023","volume-title":"Proceedings of the 35th Conference on Computational Linguistics and Speech Processing (ROCLING 2023)","author":"Lu"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446737"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSPW62465.2024.10626762"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389617"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2032"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446502"},{"key":"ref30","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","journal-title":"Transactions on Machine Learning Research."},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447523"},{"key":"ref32","article-title":"Funaudiollm: Voice understanding and generation foundation models for natural interaction between humans and 11 ms","author":"An","year":"2024"},{"key":"ref33","article-title":"The Speech Chain, Anchor books","author":"Denes","year":"1993"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268950"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1558"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639674"},{"key":"ref37","article-title":"Montreal forced aligner [computer program]","author":"McAuliffe","year":"2017"},{"key":"ref38","article-title":"Fineweb2: A sparkling update with 1000s of languages","author":"Penedo","year":"2024"},{"key":"ref39","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":"ref40","first-page":"7259","article-title":"Ascend: A spontaneous chinese-english dataset for codeswitching in multi-turn conversation","volume-title":"Proceedings of the Thirteenth Language Resources and Evaluation Conference","author":"Lovenia"}],"event":{"name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,12,6]]},"end":{"date-parts":[[2025,12,10]]}},"container-title":["2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11434577\/11433836\/11434800.pdf?arnumber=11434800","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:59:56Z","timestamp":1775192396000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434800\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434800","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}