{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T18:51:23Z","timestamp":1764874283926,"version":"3.46.0"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"JST CREST","award":["JPMJCR19A3"],"award-info":[{"award-number":["JPMJCR19A3"]}]},{"name":"JST AIP Acceleration Research","award":["JPMJCR25U5"],"award-info":[{"award-number":["JPMJCR25U5"]}]},{"name":"JSPS KAKENHI","award":["25K02788"],"award-info":[{"award-number":["25K02788"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Top. Signal Process."],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1109\/jstsp.2025.3584195","type":"journal-article","created":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T13:38:32Z","timestamp":1751290712000},"page":"827-839","source":"Crossref","is-referenced-by-count":1,"title":["Resolving Domain Mismatches in Electrolaryngeal Speech Enhancement With Linguistic Intermediates"],"prefix":"10.1109","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9118-2994","authenticated-orcid":false,"given":"Lester Phillip","family":"Violeta","sequence":"first","affiliation":[{"name":"Graduate School of Informatics, Nagoya University, Nagoya, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3172-3335","authenticated-orcid":false,"given":"Wen-Chin","family":"Huang","sequence":"additional","affiliation":[{"name":"Graduate School of Informatics, Nagoya University, Nagoya, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6564-4571","authenticated-orcid":false,"given":"Ding","family":"Ma","sequence":"additional","affiliation":[{"name":"Graduate School of Informatics, Nagoya University, Nagoya, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ryuichi","family":"Yamamoto","sequence":"additional","affiliation":[{"name":"Graduate School of Informatics, Nagoya University, Nagoya, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5047-4165","authenticated-orcid":false,"given":"Kazuhiro","family":"Kobayashi","sequence":"additional","affiliation":[{"name":"Graduate School of Informatics, Nagoya University, Nagoya, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8146-1279","authenticated-orcid":false,"given":"Tomoki","family":"Toda","sequence":"additional","affiliation":[{"name":"Information Technology Center, Nagoya University, Nagoya, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3038524"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-697"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1789"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414644"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1177\/000348948008900608"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687908"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3049336"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-676"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023033"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3402557"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-64206-2_57"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447197"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1504"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3076867"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746484"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.907344"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1066"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3047262"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413973"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3001456"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/VCCBC.2020-16"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688010"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2006.872821"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2009-439"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2011.07.007"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/AEEICB.2018.8480968"},{"key":"ref29","first-page":"546","article-title":"Mandarin electro-laryngeal speech enhancement based on statistical voice conversion and manual tone control","volume-title":"Proc. Asia-Pacific Signal Inf. Process. Assoc. Annu. Summit Conf.","author":"Qian","year":"2021"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096442"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-285"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095931"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC58517.2023.10317318"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1427"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1384"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747516"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"article-title":"Hi-Fi-CAPTAIN: High-fidelity and high-capacity conversational speech synthesis corpus developed by NICT","year":"2023","author":"Okamoto","key":"ref40"},{"key":"ref41","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho","year":"2020"},{"article-title":"Guided-TTS 2: A diffusion model for high-quality adaptive text-to-speech with untranscribed data","year":"2022","author":"Kim","key":"ref42"},{"article-title":"Classifier-free diffusion guidance","volume-title":"Proc. NeurIPS 2021 Workshop Deep Generative Models Downstream Appl.","author":"Ho","key":"ref43"},{"key":"ref44","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Kong","year":"2020"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747707"},{"key":"ref46","article-title":"RAD-TTS: Parallel flow-based TTS with robust alignment learning and diverse synthesis","volume-title":"Proc. ICML Workshop Invertible Neural Netw., Normalizing Flows, Explicit Likelihood Models","author":"Shih","year":"2021"},{"article-title":"AAS-VC: On the generalization ability of automatic alignment search based non-autoregressive sequence-to-sequence voice conversion","year":"2023","author":"Huang","key":"ref47"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446921"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10043"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-439"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413425"},{"article-title":"JSUT corpus: Free large-scale Japanese speech corpus for end-to-end speech synthesis","year":"2017","author":"Sonobe","key":"ref52"},{"article-title":"JVS corpus: Free Japanese multi-speaker voice corpus","year":"2019","author":"Takamichi","key":"ref53"},{"article-title":"CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit","year":"2012","author":"Veaux","key":"ref54"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21350"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414872"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448291"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2008-480"}],"container-title":["IEEE Journal of Selected Topics in Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/4200690\/11275987\/11059307.pdf?arnumber=11059307","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T18:37:21Z","timestamp":1764873441000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11059307\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":59,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/jstsp.2025.3584195","relation":{},"ISSN":["1932-4553","1941-0484"],"issn-type":[{"type":"print","value":"1932-4553"},{"type":"electronic","value":"1941-0484"}],"subject":[],"published":{"date-parts":[[2025,7]]}}}