{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T17:15:26Z","timestamp":1770743726406,"version":"3.49.0"},"reference-count":23,"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"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icasspw65056.2025.11011033","type":"proceedings-article","created":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T17:05:14Z","timestamp":1748365514000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["Unsupervised Rhythm and Voice Conversion of Dysarthric to Healthy Speech for ASR"],"prefix":"10.1109","author":[{"given":"Karl","family":"El Hajal","sequence":"first","affiliation":[{"name":"Idiap Research Institute,Martigny,Switzerland,CH-1920"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Enno","family":"Hermann","sequence":"additional","affiliation":[{"name":"Idiap Research Institute,Martigny,Switzerland,CH-1920"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ajinkya","family":"Kulkarni","sequence":"additional","affiliation":[{"name":"Idiap Research Institute,Martigny,Switzerland,CH-1920"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mathew","family":"Magimai.-Doss","sequence":"additional","affiliation":[{"name":"Idiap Research Institute,Martigny,Switzerland,CH-1920"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Motor Speech Disorders","author":"Duffy","year":"2012"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2391"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746585"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2481"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1645"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-49169-1_10"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-43958-7_44"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683091"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1751"},{"key":"ref10","article-title":"An Objective Evaluation Framework for Pathological Speech Synthesis","volume-title":"Proc. ITG Conference on Speech Communication","author":"Halpern"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-190"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-419"},{"key":"ref13","article-title":"SSL-TTS: Leveraging self-supervised embeddings and kNN retrieval for zero-shot multi-speaker TTS","author":"Hajal","year":"2024"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-49002-6_10"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3313515"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-011-9145-0"},{"key":"ref17","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446484"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1998.675422"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref21","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. NeurIPS","author":"Kong"},{"key":"ref22","volume-title":"The LJ speech dataset","author":"Ito","year":"2017"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3630106.3658996"}],"event":{"name":"2025 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["2025 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11010992\/11010997\/11011033.pdf?arnumber=11011033","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,28]],"date-time":"2025-05-28T04:50:48Z","timestamp":1748407848000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11011033\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icasspw65056.2025.11011033","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}