{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:17:20Z","timestamp":1774419440729,"version":"3.50.1"},"reference-count":38,"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\/icassp49660.2025.10887605","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":2,"title":["A Non-autoregressive Model for Joint STT and TTS"],"prefix":"10.1109","author":[{"given":"Vishal","family":"Sunder","sequence":"first","affiliation":[{"name":"The Ohio State University,Columbus,OH,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Brian","family":"Kingsbury","sequence":"additional","affiliation":[{"name":"IBM Research,Yorktown Heights,NY,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"George","family":"Saon","sequence":"additional","affiliation":[{"name":"IBM Research,Yorktown Heights,NY,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Samuel","family":"Thomas","sequence":"additional","affiliation":[{"name":"IBM Research,Yorktown Heights,NY,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Slava","family":"Shechtman","sequence":"additional","affiliation":[{"name":"IBM Research,Israel"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hagai","family":"Aronowitz","sequence":"additional","affiliation":[{"name":"IBM Research,Israel"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eric","family":"Fosler-Lussier","sequence":"additional","affiliation":[{"name":"The Ohio State University,Columbus,OH,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luis","family":"Lastras","sequence":"additional","affiliation":[{"name":"IBM Research,Yorktown Heights,NY,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"5410","article-title":"Almost unsupervised text to speech and automatic speech recognition","volume-title":"International Conference on machine learning","author":"Ren"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.393"},{"key":"ref3","article-title":"Lauragpt: Listen, attend, understand, and regenerate audio with gpt","author":"Chen","year":"2023"},{"key":"ref4","article-title":"Seamlessm4t-massively multilingual & multimodal machine translation","author":"Barrault","year":"2023"},{"key":"ref5","article-title":"Speechverse: A large-scale generalizable audio language model","author":"Das","year":"2024"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3434425"},{"key":"ref7","article-title":"Funaudiollm: Voice understanding and generation foundation models for natural interaction between humans and llms","author":"SpeechTeam","year":"2024"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.549"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref10","article-title":"Fastspeech: Fast, robust and controllable text to speech","volume":"32","author":"Ren","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022774"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747862"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446807"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.154"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2404"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.402"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095186"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389803"},{"key":"ref19","first-page":"12 449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref20","article-title":"Layer normalization","author":"Lei Ba","year":"2016"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-439"},{"key":"ref22","first-page":"28 492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International Conference on machine learning","author":"Radford"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1345"},{"key":"ref24","article-title":"The lj speech dataset","author":"Ito","year":"2017"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1584"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref30","first-page":"17 022","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"Kong","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-711"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1117\/12.2520589"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref35","first-page":"1058","article-title":"Regularization of neural networks using dropconnect","volume-title":"International Conference on machine learning","author":"Wan"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683706"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-911"},{"key":"ref38","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"Ren","year":"2020"}],"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\/10887605.pdf?arnumber=10887605","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:52Z","timestamp":1774416172000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10887605\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10887605","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}