{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T14:56:11Z","timestamp":1777733771411,"version":"3.51.4"},"reference-count":43,"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\/icassp49660.2025.10888830","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":8,"title":["Generative Speech Foundation Model Pretraining for High-Quality Speech Extraction and Restoration"],"prefix":"10.1109","author":[{"given":"Pin-Jui","family":"Ku","sequence":"first","affiliation":[{"name":"NVIDIA,USA"}]},{"given":"Alexander H.","family":"Liu","sequence":"additional","affiliation":[{"name":"NVIDIA,USA"}]},{"given":"Roman","family":"Korostik","sequence":"additional","affiliation":[{"name":"NVIDIA,USA"}]},{"given":"Sung-Feng","family":"Huang","sequence":"additional","affiliation":[{"name":"NVIDIA,USA"}]},{"given":"Szu-Wei","family":"Fu","sequence":"additional","affiliation":[{"name":"NVIDIA,USA"}]},{"given":"Ante","family":"Juki\u0107","sequence":"additional","affiliation":[{"name":"NVIDIA,USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2364452"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2416653"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/1084713808326455"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-1084"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2409"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2291"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414060"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1428"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746901"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096064"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095258"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3294692"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832332"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1441"},{"key":"ref16","article-title":"Generative pre-training for speech with flow matching","volume-title":"Proc. ICLR","author":"Liu"},{"key":"ref17","article-title":"Voicebox: Text-guided multilingual universal speech generation at scale","author":"Le","year":"2023"},{"key":"ref18","article-title":"Audiobox: Unified audio generation with natural language prompts","author":"Vyas","year":"2023"},{"key":"ref19","article-title":"NeMo: a toolkit for conversational ai and large language models","author":"Harper","year":"2023"},{"key":"ref20","article-title":"Flow matching for generative modeling","volume-title":"Proc. ICLR","author":"Lipman"},{"key":"ref21","article-title":"Neural ordinary differential equations","volume-title":"Proc. NeurIPS","author":"Chen"},{"key":"ref22","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. NeuIPS","author":"Kong"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref24","article-title":"Train short, test long: Attention with linear biases enables input length extrapolation","volume-title":"Proc. ICLR","author":"Press"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref27","article-title":"Noisy speech database for training speech enhancement algorithms and TTS models","author":"Valentini-Botinhao","year":"2017"},{"key":"ref28","article-title":"High-fidelity audio compression with improved RVQGAN","volume-title":"Proc. NeurIPS","author":"Kumar"},{"key":"ref29","article-title":"LibriMix: An open-source dataset for generalizable speech separation","author":"Cosentino","year":"2020"},{"key":"ref30","doi-asserted-by":"crossref","DOI":"10.1109\/ICASSP40776.2020.9054683","article-title":"Improving speaker discrimination of target speech extraction with time-domain speakerbeam","volume-title":"Proc. ICASSP","author":"Delcroix"},{"key":"ref31","article-title":"Classifier-free diffusion guidance","volume-title":"Proc. NeurIPS","author":"Ho"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2585878"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683855"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096680"},{"key":"ref36","doi-asserted-by":"crossref","DOI":"10.1109\/ICASSP49357.2023.10097255","article-title":"HIFI++: A unified framework for bandwidth extension and speech enhancement","volume-title":"Proc. ICASSP","author":"Andreev"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11252"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3285241"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3407533"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448315"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1397"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747340"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"}],"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\/10888830.pdf?arnumber=10888830","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:20:30Z","timestamp":1774416030000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888830\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888830","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}