{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T07:19:23Z","timestamp":1777619963098,"version":"3.51.4"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004663","name":"MOST-Taiwan","doi-asserted-by":"publisher","award":["107-2221-E-001-008-MY3"],"award-info":[{"award-number":["107-2221-E-001-008-MY3"]}],"id":[{"id":"10.13039\/501100004663","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,12,13]]},"DOI":"10.1109\/asru51503.2021.9687908","type":"proceedings-article","created":{"date-parts":[[2022,2,3]],"date-time":"2022-02-03T20:31:00Z","timestamp":1643920260000},"page":"650-657","source":"Crossref","is-referenced-by-count":13,"title":["Mandarin Electrolaryngeal Speech Voice Conversion with Sequence-to-Sequence Modeling"],"prefix":"10.1109","author":[{"given":"Ming-Chi","family":"Yen","sequence":"first","affiliation":[{"name":"National Taiwan University,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wen-Chin","family":"Huang","sequence":"additional","affiliation":[{"name":"Nagoya University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kazuhiro","family":"Kobayashi","sequence":"additional","affiliation":[{"name":"Nagoya University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu-Huai","family":"Peng","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Academia Sinica,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shu-Wei","family":"Tsai","sequence":"additional","affiliation":[{"name":"National Cheng Kung University Hospital,Dept. of Otolaryngology,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Tsao","sequence":"additional","affiliation":[{"name":"Research Center for Information Technology Innovation, Academia Sinica,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomoki","family":"Toda","sequence":"additional","affiliation":[{"name":"Nagoya University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jyh-Shing Roger","family":"Jang","sequence":"additional","affiliation":[{"name":"National Taiwan University,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hsin-Min","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Academia Sinica,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682380"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2892235"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.23919\/Eusipco47968.2020.9287721"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21236\/ADA073139"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1250\/ast.11.71"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1979.1163209"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"328","DOI":"10.1109\/89.701361","article-title":"A parametric formulation of the generalized spectral subtraction method","volume":"6","author":"sim","year":"1998","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"ref15","article-title":"Spectral subtraction with variance reduced noise spectrum estimates","author":"wojcicki","year":"2006","journal-title":"Proceedings of the 11th Australasian International Conference on Speech Science and Technoligy"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/89.397090"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3001456"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178838"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1002\/ecja.4400660203"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947513"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8269007"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2011.07.007"},{"key":"ref6","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"0","journal-title":"Proceedings of ICLR"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2013.2286917"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"ref8","article-title":"Voice Transformer Network: Sequence-to-Sequence Voice Conversion Using Transformer with Text-to-Speech Pretraining","author":"huang","year":"2019","journal-title":"ArXiv e-prints"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553154"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004008"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.E97.D.1429"},{"key":"ref20","author":"huang","year":"2005","journal-title":"Development of Taiwan Manadarin hearing in noise test"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref21","first-page":"23","article-title":"Sinica cospro and toolkit: Corpora and platform of mandarin chinese fluent speech","author":"tseng","year":"0","journal-title":"Proceedings of O-COCOSDA"},{"key":"ref24","article-title":"Parallel Wave-gan: A Fast Waveform Generation Model Based on Generative Adversarial Networks with Multi-Resolution Spectrogram","author":"yamamoto","year":"0","journal-title":"Proceedings of ICASSP"},{"key":"ref23","article-title":"ESPnet-TTS: Unified, Reproducible, and Integratable Open Source End-to-End Text-to-Speech Toolkit","author":"hayashi","year":"2019","journal-title":"ArXiv e-prints"},{"key":"ref26","article-title":"Speaker-dependent WaveNet vocoder","author":"tamamori","year":"0","journal-title":"Proceedings of Interspeech"},{"key":"ref25","article-title":"WaveNet: A Generative Model for Raw Audio","author":"van den oord","year":"2016","journal-title":"ArXiv e-prints"}],"event":{"name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Cartagena, Colombia","start":{"date-parts":[[2021,12,13]]},"end":{"date-parts":[[2021,12,17]]}},"container-title":["2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9687821\/9687855\/09687908.pdf?arnumber=9687908","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,16]],"date-time":"2022-05-16T20:42:24Z","timestamp":1652733744000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9687908\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,13]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/asru51503.2021.9687908","relation":{},"subject":[],"published":{"date-parts":[[2021,12,13]]}}}