{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:55:24Z","timestamp":1777658124231,"version":"3.51.4"},"reference-count":47,"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\/icassp49660.2025.10887856","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":6,"title":["AnCoGen: Analysis, Control and Generation of Speech with a Masked Autoencoder"],"prefix":"10.1109","author":[{"given":"Samir","family":"Sadok","sequence":"first","affiliation":[{"name":"Inria at Univ. Grenoble Alpes,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Simon","family":"Leglaive","sequence":"additional","affiliation":[{"name":"CentraleSupélec,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Laurent","family":"Girin","sequence":"additional","affiliation":[{"name":"Univ. Grenoble Alpes,CNRS, Grenoble INP, GIPSA-Lab,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ga\u00ebl","family":"Richard","sequence":"additional","affiliation":[{"name":"LTCI, Télécom Paris, Institut Polytechnique de,Paris,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xavier","family":"Alameda-Pineda","sequence":"additional","affiliation":[{"name":"Inria at Univ. Grenoble Alpes,France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-66286-7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1986.1164910"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/89.622558"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.2307\/3680788"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1993.319365"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(96)00038-6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(90)90021-Z"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/89.759041"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1250\/ast.27.349"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref12","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2023","journal-title":"Trans. Mach. Learn. Res"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-475"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/icasspw59220.2023.10193151"},{"key":"ref17","article-title":"Hifi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Adv. Neural Inform. Proc. Syst. (NeurIPS)","author":"Kong"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461329"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389718"},{"key":"ref21","article-title":"Neural discrete representation learning","volume-title":"Adv. Neural Inform. Proc. Syst. (NeurIPS)","author":"Van Den Oord"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/icasspw59220.2023.10193151"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746484"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref25","article-title":"Attention is all you need","volume-title":"Adv. Neural Inform. Proc. Syst. (NeurIPS)","author":"Vaswani"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2537"},{"key":"ref27","article-title":"Phaseaware speech enhancement with deep complex U-net","volume-title":"Int. Conf. Learn. Repres. (ICLR)","author":"Choi"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2205"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref31","article-title":"DEMAND: a collection of multichannel recordings of acoustic noise in diverse environments","volume-title":"Int. Congr. Acoust. (ICA)","author":"Thiemann"},{"key":"ref32","article-title":"Pedalboard","author":"Sobot","year":"2021"},{"key":"ref33","article-title":"Librimix: An open-source dataset for generalizable speech separation","author":"Cosentino","year":"2020"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2821"},{"key":"ref35","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683855"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-407"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096680"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746108"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-317"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853678"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1121\/1.2951592"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01802"},{"key":"ref47","article-title":"Generating diverse highfidelity images with VQ-VAE-2","volume-title":"Adv. Neural Inform. Proc. Syst. (NeurIPS)","author":"Razavi"}],"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\/10887856.pdf?arnumber=10887856","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:22Z","timestamp":1774416142000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10887856\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10887856","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}