{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:25:44Z","timestamp":1775229944584,"version":"3.50.1"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10888566","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":7,"title":["LLM based Text Generation for Improved Low-resource Speech Recognition Models"],"prefix":"10.1109","author":[{"given":"Tohru","family":"Nagano","sequence":"first","affiliation":[{"name":"IBM Research,Tokyo,Japan"}]},{"given":"Gakuto","family":"Kurata","sequence":"additional","affiliation":[{"name":"IBM Research,Tokyo,Japan"}]},{"given":"Samuel","family":"Thomas","sequence":"additional","affiliation":[{"name":"IBM Research,USA"}]},{"given":"Hong-Kwang J.","family":"Kuo","sequence":"additional","affiliation":[{"name":"IBM Research,USA"}]},{"given":"Daniel","family":"Bolanos","sequence":"additional","affiliation":[{"name":"IBM Research,USA"}]},{"given":"Hyun","family":"Jung","sequence":"additional","affiliation":[{"name":"IBM Research,USA"}]},{"given":"George","family":"Saon","sequence":"additional","affiliation":[{"name":"IBM Research,USA"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","year":"2024"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.44"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-industry.15"},{"key":"ref4","first-page":"13","article-title":"ChatGPT as data augmentation for compositional generalization: A case study in open intent detection","volume-title":"Proceedings of the Fifth Workshop on Financial Technology and Natural Language Processing and the Second Multimodal AI For Financial Forecasting","author":"Fang"},{"key":"ref5","article-title":"Scaling speech technology to 1,000+ languages","author":"Pratap","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462682"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094796"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003790"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.618"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11123"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095186"},{"key":"ref12","article-title":"An embarrassingly simple approach for llm with strong asr capacity","author":"Ma","year":"2024"},{"key":"ref13","article-title":"Common voice: A massively-multilingual speech corpus","author":"Ardila","year":"2020"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389689"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-industry.85"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-911"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688157"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2005-338"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-632"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404790"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178778"},{"key":"ref24","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/e17-2068"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1705"},{"key":"ref27","article-title":"Openvoice: Versatile instant voice cloning","author":"Qin","year":"2024"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688101"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1349"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10888566.pdf?arnumber=10888566","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:21:11Z","timestamp":1774416071000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888566\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888566","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}