{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:05:09Z","timestamp":1776888309894,"version":"3.51.2"},"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\/icassp49660.2025.10890277","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":5,"title":["High-Resolution Speech Restoration with Latent Diffusion Model"],"prefix":"10.1109","author":[{"given":"Tushar","family":"Dhyani","sequence":"first","affiliation":[{"name":"Sony Europe B.V.,Stuttgart,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Florian","family":"Lux","sequence":"additional","affiliation":[{"name":"University of Stuttgart,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michele","family":"Mancusi","sequence":"additional","affiliation":[{"name":"Sony Europe B.V.,Stuttgart,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Giorgio","family":"Fabbro","sequence":"additional","affiliation":[{"name":"Sony Europe B.V.,Stuttgart,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fritz","family":"Hohl","sequence":"additional","affiliation":[{"name":"Sony Europe B.V.,Stuttgart,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ngoc Thang","family":"Vu","sequence":"additional","affiliation":[{"name":"University of Stuttgart,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-11026"},{"key":"ref2","article-title":"Resemble Enhance","author":"Niu","year":"2024"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095557"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA58266.2023.10248089"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164453"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2011.09.003"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2409"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2995273"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854590"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1121\/1.408434"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/S0166-2236(02)02191-4"},{"key":"ref12","article-title":"Universal speech enhancement with score-based diffusion","author":"Serr\u00e0","year":"2022"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA58266.2023.10248157"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.30420\/456164051"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3294692"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095258"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.3037485"},{"key":"ref18","article-title":"Generative adversarial networks","author":"Goodfellow","year":"2014"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2022.3204461"},{"key":"ref21","article-title":"Flow Matching for Generative Modeling","volume-title":"ICLR","author":"Lipman"},{"key":"ref22","article-title":"Noisy speech database for training speech enhancement algorithms and tts models","author":"Valentini-Botinhao","year":"2017"},{"key":"ref23","article-title":"pyloudnorm: A simple yet flexible loudness meter in python","author":"Steinmetz","year":"2021","journal-title":"150th AES Convention"},{"key":"ref24","article-title":"AudioLDM: Text-to-Audio Generation with Latent Diffusion Models","volume-title":"ICML","author":"Liu"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2024.3399607"},{"key":"ref26","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"Proceedings of the 38th International Conference on Machine Learning","volume":"139","author":"Nichol"},{"key":"ref27","first-page":"6840","article-title":"Denoising Diffusion Probabilistic Models","volume-title":"NeurIPS","volume":"33","author":"Ho"},{"key":"ref28","first-page":"28708","article-title":"Masked autoencoders that listen","volume-title":"NeurIPS","volume":"35","author":"Huang"},{"key":"ref29","first-page":"17022","article-title":"HiFi-GAN: Generative Adversarial Networks for efficient and high fidelity Speech Synthesis","volume-title":"NeurIPS","volume":"33","author":"Kong"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.7488\/ds\/2645"},{"key":"ref31","article-title":"96kHz version of the CSTR VCTK Corpus","author":"Veaux","year":"2017"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/SLTU.2018-14"},{"key":"ref33","first-page":"6532","article-title":"Open-source Multi-speaker Corpora of the English Accents in the British Isles","volume-title":"LREC","author":"Demirsahin"},{"key":"ref34","first-page":"6504","article-title":"Crowdsourcing Latin American Spanish for Low-Resource Text-to-Speech","volume-title":"LREC","author":"Guevara-Rukoz"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1096"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-299"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133208"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495701"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10888146"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414878"},{"key":"ref41","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-138"}],"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\/10890277.pdf?arnumber=10890277","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:35Z","timestamp":1774416335000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890277\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890277","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}