{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T05:51:40Z","timestamp":1775541100352,"version":"3.50.1"},"reference-count":53,"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":"JSPS KAKENHI","award":["JP23K21945"],"award-info":[{"award-number":["JP23K21945"]}]},{"name":"JSPS KAKENHI","award":["JP24K02959"],"award-info":[{"award-number":["JP24K02959"]}]},{"name":"JSPS KAKENHI","award":["JP25K00471"],"award-info":[{"award-number":["JP25K00471"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3677555","type":"journal-article","created":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T19:57:30Z","timestamp":1774468650000},"page":"50191-50203","source":"Crossref","is-referenced-by-count":0,"title":["Controllable End-to-End Neural Source\u2013Filter Vocoder With Low-Dimensional Speech Parameters and Data Augmentation"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-4860-5400","authenticated-orcid":false,"given":"Sumiharu","family":"Kobayashi","sequence":"first","affiliation":[{"name":"Graduate School of Engineering, Tohoku University, Sendai, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1321-641X","authenticated-orcid":false,"given":"Tetsuo","family":"Kosaka","sequence":"additional","affiliation":[{"name":"Graduate School of Science and Engineering, Yamagata University, Yonezawa, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2278-0429","authenticated-orcid":false,"given":"Takashi","family":"Nose","sequence":"additional","affiliation":[{"name":"Graduate School of Engineering, Tohoku University, Sendai, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/89.397089"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00085-5"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1250\/ast.27.349"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1515\/9783110873429"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2956145"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446960"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TAU.1968.1161952"},{"issue":"132","key":"ref8","first-page":"110","article-title":"Importance of higher formants in discriminating \/i\/ and \/e\/ in Nagai, Yamagata: A perceptual experiment using synthesized speech","author":"Satou","year":"1983","journal-title":"Jpn. Linguistics"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-1622"},{"key":"ref10","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. NeurIPS","author":"Kong"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095298"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/GCCE62371.2024.10760681"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/1240624.1240859"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.jdmm.2025.100992"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1121\/1.3212921"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1121\/1.383940"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1121\/1.1912679"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1002\/9781444301007.ch22"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016"},{"key":"ref21","first-page":"2410","article-title":"Efficient neural audio synthesis","volume-title":"Proc. PMLR","author":"Kalchbrenner"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2765202"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref25","article-title":"MelGAN: Generative adversarial networks for conditional waveform synthesis","volume-title":"Proc. NeurIPS","volume":"32","author":"Kumar"},{"key":"ref26","article-title":"DDSP: Differentiable digital signal processing","volume-title":"Proc. ICLR","author":"Engel"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00293"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3321191"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447948"},{"key":"ref30","article-title":"BigVGAN: A universal neural vocoder with large-scale training","volume-title":"Proc. ICLR","author":"Lee"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682897"},{"key":"ref32","article-title":"Scyclone: High-quality and parallel-data-free voice conversion using spectrogram and cycle-consistent adversarial networks","author":"Tanaka","year":"2020","journal-title":"arXiv:2005.03334"},{"key":"ref33","article-title":"JVS corpus: Free Japanese multi-speaker voice corpus","author":"Takamichi","year":"2019","journal-title":"arXiv:1908.06248"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1993.319366"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-021-00225-4"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3628428"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2023-33"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1977.1162905"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1121\/1.410376"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1121\/1.1344156"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-68"},{"key":"ref43","article-title":"Maximum entropy spectral analysis","volume-title":"Ph.D. thesis, Dept. Geophys., Stanford Univ.","author":"Burg","year":"1975"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1016"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-439"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1121\/1.383319"},{"key":"ref47","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1098\/rstb.1992.0070"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1017\/S0025100305002124"},{"key":"ref50","article-title":"PromptTTS 2: Describing and generating voices with text prompt","volume-title":"Proc. ICLR","author":"Leng"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446889"},{"key":"ref52","first-page":"3290","article-title":"Acoustic characteristics of Japanese vowels","volume-title":"Proc. Integr. Comput.-Aided Eng.","author":"Hirahara"},{"key":"ref53","article-title":"Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis","volume-title":"Proc. ICLR","author":"Siuzdak"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11455988.pdf?arnumber=11455988","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T04:56:49Z","timestamp":1775537809000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11455988\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3677555","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}