{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T19:55:00Z","timestamp":1781898900824,"version":"3.54.5"},"reference-count":33,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Mid-Career Research Fund"},{"DOI":"10.13039\/501100004704","name":"National Research Council of Thailand","doi-asserted-by":"publisher","award":["N42A670175"],"award-info":[{"award-number":["N42A670175"]}],"id":[{"id":"10.13039\/501100004704","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Open J. Comput. Soc."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/ojcs.2026.3696985","type":"journal-article","created":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T19:45:05Z","timestamp":1781293505000},"page":"1236-1247","source":"Crossref","is-referenced-by-count":0,"title":["Attention-Driven Alaryngeal Speech Enhancement via Discrete Representation Learning and Timbre-Preserving Augmentation"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-0746-8266","authenticated-orcid":false,"given":"Hnin Yadana","family":"Lwin","sequence":"first","affiliation":[{"name":"Department of Electronics and Telecommunication Engineering, King Mongkut's University of Technology Thonburi, Bangkok, Thailand"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2957-6084","authenticated-orcid":false,"given":"Wuttipong","family":"Kumwilaisak","sequence":"additional","affiliation":[{"name":"Department of Electronics and Telecommunication Engineering, King Mongkut's University of Technology Thonburi, Bangkok, Thailand"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4064-4882","authenticated-orcid":false,"given":"Chatchawarn","family":"Hansakunbuntheung","sequence":"additional","affiliation":[{"name":"Digital Healthcare Platform Innovation Group, National Science and Technology Development Agency, Pathumthani, Thailand"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8240-2772","authenticated-orcid":false,"given":"Nattanun","family":"Thatphithakkul","sequence":"additional","affiliation":[{"name":"Digital Healthcare Platform Innovation Group, National Science and Technology Development Agency, Pathumthani, Thailand"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"issue":"S2","key":"ref1","first-page":"115","article-title":"Perceptual evaluation of Alaryngeal speech","volume":"36","author":"Rosso","year":"2012","journal-title":"Collegium Antropologicum"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-419"},{"key":"ref3","article-title":"Esophageal to laryngeal voice conversion using a sequence to sequence mapping model including an attention mechanism","volume":"7","author":"Ezzine","year":"2022","journal-title":"Clin. Surg."},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447464"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10868"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNSRE.2025.3570383"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICSLP.1996.607475"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.E93.D.2472"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1250\/ast.23.69"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvoice.2024.07.016"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i13.29411"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553236"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682897"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2280"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414851"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3471926"},{"key":"ref18","article-title":"discrete-wavlm-codec: A neural speech codec based on discrete WavLM representations","volume-title":"GitHub","author":"Libera","year":"2024"},{"key":"ref19","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kong","year":"2020"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref21","article-title":"Resemblyzer","year":"2020"},{"key":"ref22","article-title":"MeVoice: A Thai alaryngeal speech corpus","author":"Hansakunbuntheung","year":"2019","journal-title":"Nat. Sci. Technol. Develop. Agency"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.nlposs-1.4"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-1828"},{"key":"ref25","article-title":"Atos medical YouTube channel"},{"key":"ref26","first-page":"4218","article-title":"Common Voice: A massively-multilingual speech corpus","volume-title":"Proc. 12th Lang. Resour. Eval. Conf.","author":"Ardila","year":"2020"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-03577-2"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2219"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-299"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3580706"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1017"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746901"}],"container-title":["IEEE Open Journal of the Computer Society"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8782664\/11319293\/11561057.pdf?arnumber=11561057","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T19:42:58Z","timestamp":1781898178000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11561057\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/ojcs.2026.3696985","relation":{},"ISSN":["2644-1268"],"issn-type":[{"value":"2644-1268","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}