{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T20:08:21Z","timestamp":1784059701124,"version":"3.55.0"},"reference-count":25,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"}],"funder":[{"DOI":"10.13039\/501100003710","name":"Korea Health Industry Development Institute","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003710","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["clinicalkey.com","clinicalkey.com.au","clinicalkey.es","clinicalkey.fr","clinicalkey.jp","jvoice.org","elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Voice"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.jvoice.2026.06.032","type":"journal-article","created":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T20:26:33Z","timestamp":1783974393000},"update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"title":["Restoring Over-Attenuated Sustained Vowel Phonations in Smartphone Calls of COPD Patients Using U-Net and Speech Foundation Models"],"prefix":"10.1016","author":[{"given":"Hyora","family":"Lee","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hyein","family":"Ryu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sang Mee","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sunga","family":"Kong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Myung Jin","family":"Chung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juhee","family":"Cho","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5937-9671","authenticated-orcid":false,"given":"Hye Yun","family":"Park","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2591-0129","authenticated-orcid":false,"given":"Taeyoung","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.jvoice.2026.06.032_bib1","series-title":"Leading Practices for the Future of Telemedicine","author":"Keelara","year":"2025"},{"key":"10.1016\/j.jvoice.2026.06.032_bib2","doi-asserted-by":"crossref","first-page":"1165","DOI":"10.1044\/2022_JSLHR-22-00522","article-title":"Maximum phonation time as a surrogate marker for airway clearance physiologic capacity and pulmonary function in individuals with amyotrophic lateral sclerosis","volume":"66","author":"Gray","year":"2023","journal-title":"J Speech Lang Hear Res"},{"key":"10.1016\/j.jvoice.2026.06.032_bib3","doi-asserted-by":"crossref","first-page":"1320","DOI":"10.1038\/s41597-024-04171-6","article-title":"Slovak database of speech affected by neurodegenerative diseases","volume":"11","author":"Rusko","year":"2024","journal-title":"Sci Data"},{"key":"10.1016\/j.jvoice.2026.06.032_bib4","doi-asserted-by":"crossref","DOI":"10.1038\/s41531-025-00913-4","article-title":"Speech and language biomarkers for Parkinson\u2019s disease prediction, early diagnosis and progression","volume":"11","author":"Cao","year":"2025","journal-title":"npj Parkinsons Dis"},{"key":"10.1016\/j.jvoice.2026.06.032_bib5","series-title":"Proceedings of Interspeech 2024","first-page":"1410","article-title":"Sustained vowels for pre-vs post-treatment COPD classification","author":"Triantafyllopoulos","year":"2024"},{"key":"10.1016\/j.jvoice.2026.06.032_bib6","unstructured":"3GPP. 3rd Generation Partnership Project; Technical Specification Group Services and System Aspects; Codec for Enhanced Voice Services (EVS); Detailed Algorithmic Description (Release 14). General description of the coder 2017 19 23."},{"key":"10.1016\/j.jvoice.2026.06.032_bib7","series-title":"Deepfilternet: a low complexity speech enhancement framework for full-band audio based on deep filtering. ICASSP 2022\u20132022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).","first-page":"7407","author":"Schr\u00f6ter","year":"2022"},{"key":"10.1016\/j.jvoice.2026.06.032_bib8","series-title":"2022 International Workshop on Acoustic Signal Enhancement (IWAENC)","first-page":"1","article-title":"Deepfilternet2: towards real-time speech enhancement on embedded devices for full-band audio","author":"Schr\u00f6ter","year":"2022"},{"key":"10.1016\/j.jvoice.2026.06.032_bib9","unstructured":"Schr\u00f6ter H., Escalante-B A.N., Rosenkranz T., Maier A. DeepFilterNet: Perceptually Motivated Real-Time Speech Enhancement. Proceedings of Interspeech 2023. Dublin, Ireland: ISCA; 2023:2008\u20132009."},{"key":"10.1016\/j.jvoice.2026.06.032_bib10","series-title":"Proceedings of Interspeech 2022","first-page":"4232","article-title":"VoiceFixer: a unified framework for high-fidelity speech restoration","author":"Liu","year":"2022"},{"key":"10.1016\/j.jvoice.2026.06.032_bib11","doi-asserted-by":"crossref","unstructured":"K. Byun J. Filos E. Visser S. Moon VC-ENHANCE: speech restoration with integrated noise suppression and voice conversion arXiv preprint arXiv:240906126 2024.","DOI":"10.21437\/Interspeech.2025-998"},{"key":"10.1016\/j.jvoice.2026.06.032_bib12","doi-asserted-by":"crossref","unstructured":"K. Byun J. Filos E. Visser S. Moon Voice-ENHANCE: Speech Restoration using a Diffusion-based Voice Conversion Framework arXiv preprint arXiv:250515254 2025.","DOI":"10.21437\/Interspeech.2025-998"},{"key":"10.1016\/j.jvoice.2026.06.032_bib13","doi-asserted-by":"crossref","unstructured":"T. Sainburg A. Zorea Noisereduce: Domain general noise reduction for time series signals arXiv preprint arXiv:241217851 2024.","DOI":"10.1038\/s41598-025-13108-x"},{"key":"10.1016\/j.jvoice.2026.06.032_bib14","series-title":"Proceedings of the 2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","first-page":"732","article-title":"Lung disease classification using deep convolutional neural network","author":"Tariq","year":"2019"},{"key":"10.1016\/j.jvoice.2026.06.032_bib15","unstructured":"D. Stoller S. Ewert S. Dixon Wave-u-net: A multi-scale neural network for end-to-end audio source separation arXiv preprint arXiv:180603185 2018."},{"key":"10.1016\/j.jvoice.2026.06.032_bib16","series-title":"Proceedings of the 40th International Conference on Machine Learning (ICML)","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2023"},{"key":"10.1016\/j.jvoice.2026.06.032_bib17","first-page":"12449","article-title":"Wav2Vec 2.0: a framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"10.1016\/j.jvoice.2026.06.032_bib18","unstructured":"H. Ameer S. Latif R. Latif S. Mukhtar. Whisper in focus: Enhancing stuttered speech classification with encoder layer optimization. arXiv preprint arXiv:231105203 2023."},{"key":"10.1016\/j.jvoice.2026.06.032_bib19","series-title":"Proceedings of Interspeech 2021","first-page":"2706","article-title":"Whisper speech enhancement using joint variational autoencoder for improved speech recognition","author":"Agrawal","year":"2021"},{"key":"10.1016\/j.jvoice.2026.06.032_bib20","doi-asserted-by":"crossref","first-page":"2584","DOI":"10.1016\/j.csbj.2025.06.022","article-title":"Ranking pre-trained speech embeddings in Parkinson's disease detection: does Wav2Vec 2.0 outperform its 1.0 version across speech modes and languages?","volume":"27","author":"Klempir","year":"2025","journal-title":"Comput Struct Biotechnol J"},{"key":"10.1016\/j.jvoice.2026.06.032_bib21","unstructured":"T.I. Tamiti B. Joshi R. Hasan\u00a0et al. A high-fidelity speech super resolution network using a complex global attention module with spectro-temporal loss et al.arXiv preprint arXiv:250700229 In:\u00a0et al.(Ed.), arXiv preprint arXiv:250700229 2025."},{"key":"10.1016\/j.jvoice.2026.06.032_bib22","series-title":"Speech and Signal Processing (ICASSP)","first-page":"626","article-title":"SDR\u2014half-baked or well done? ICASSP 2019\u20132019 IEEE International Conference on Acoustics,","author":"Le Roux","year":"2019"},{"key":"10.1016\/j.jvoice.2026.06.032_bib23","doi-asserted-by":"crossref","first-page":"2125","DOI":"10.1109\/TASL.2011.2114881","article-title":"An algorithm for intelligibility prediction of time\u2013frequency weighted noisy speech","volume":"19","author":"Taal","year":"2011","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"10.1016\/j.jvoice.2026.06.032_bib24","series-title":"Speech and Signal Processing (ICASSP)","first-page":"6493","article-title":"DNSMOS: A non-intrusive perceptual objective speech quality metric to evaluate noise suppressors. ICASSP 2021\u20132021 IEEE International Conference on Acoustics,","author":"Reddy","year":"2021"},{"key":"10.1016\/j.jvoice.2026.06.032_bib25","doi-asserted-by":"crossref","unstructured":"Reddy CK, Gopal V, Cutler R. DNSMOS P.835: A non-intrusive perceptual objective speech quality metric to evaluate noise suppressors. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Singapore: IEEE; 2022:886\u2013890.","DOI":"10.1109\/ICASSP43922.2022.9746108"}],"container-title":["Journal of Voice"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0892199726003152?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0892199726003152?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T19:31:56Z","timestamp":1784057516000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0892199726003152"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":25,"alternative-id":["S0892199726003152"],"URL":"https:\/\/doi.org\/10.1016\/j.jvoice.2026.06.032","relation":{},"ISSN":["0892-1997"],"issn-type":[{"value":"0892-1997","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Restoring Over-Attenuated Sustained Vowel Phonations in Smartphone Calls of COPD Patients Using U-Net and Speech Foundation Models","name":"articletitle","label":"Article Title"},{"value":"Journal of Voice","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jvoice.2026.06.032","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Voice Foundation. Published by Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}]}}