{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T14:30:34Z","timestamp":1780756234965,"version":"3.54.1"},"reference-count":64,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Keisuke Matsubara was interning at NICT"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/taslp.2023.3275032","type":"journal-article","created":{"date-parts":[[2023,5,11]],"date-time":"2023-05-11T01:16:14Z","timestamp":1683767774000},"page":"1902-1915","source":"Crossref","is-referenced-by-count":12,"title":["Harmonic-Net: Fundamental Frequency and Speech Rate Controllable Fast Neural Vocoder"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2935-668X","authenticated-orcid":false,"given":"Keisuke","family":"Matsubara","sequence":"first","affiliation":[{"name":"Graduate School of System Informatics, Kobe University, Kobe, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9913-4647","authenticated-orcid":false,"given":"Takuma","family":"Okamoto","sequence":"additional","affiliation":[{"name":"National Institute of Information and Communications Technology, Kyoto, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9808-0250","authenticated-orcid":false,"given":"Ryoichi","family":"Takashima","sequence":"additional","affiliation":[{"name":"Graduate School of System Informatics, Kobe University, Kobe, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5005-7679","authenticated-orcid":false,"given":"Tetsuya","family":"Takiguchi","sequence":"additional","affiliation":[{"name":"Graduate School of System Informatics, Kobe University, Kobe, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"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":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hisashi","family":"Kawai","sequence":"additional","affiliation":[{"name":"National Institute of Information and Communications Technology, Kyoto, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"125","article-title":"WaveNet: A generative model for raw audio","volume-title":"Proc. ISCA Speech Synth. Workshop","author":"Oord","year":"2016"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref3","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim","year":"2021"},{"key":"ref4","article-title":"Char2Wav: End-to-end speech synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Sotelo","year":"2017"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-314"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00085-5"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178768"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2835720"},{"key":"ref10","first-page":"2415","article-title":"Efficient neural audio synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kalchbrenner","year":"2018"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1984"},{"key":"ref13","article-title":"ClariNet: Parallel wave generation in end-to-end text-to-speech","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ping","year":"2019"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref16","first-page":"14910","article-title":"MelGAN: Generative adversarial networks for conditional waveform synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kumar","year":"2019"},{"key":"ref17","article-title":"WaveGrad: Estimating gradients for waveform generation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen","year":"2021"},{"key":"ref18","article-title":"DiffWave: A versatile diffusion model for audio synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kong","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383551"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415087"},{"key":"ref21","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.","author":"Kong","year":"2020"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2013.2251852"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2017.01.008"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.2307\/3680822"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-845"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1016"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688194"},{"key":"ref29","article-title":"Chunked autoregressive GAN for conditional waveform synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Morrison","year":"2022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746713"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-831"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1121\/1.4919349"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3061245"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2918"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2558"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2956145"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3051765"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-517"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3118033"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1986.1164910"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683398"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2970241"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3188"},{"key":"ref44","article-title":"DDSP: Differentiable digital signal processing","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Engel","year":"2020"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3089565"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1993.319366"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(90)90021-Z"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8269007"},{"key":"ref49","volume-title":"Discrete-Time Signal Processing","author":"Oppenheim","year":"1999"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2022.01.003"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3164361"},{"key":"ref52","first-page":"1558","article-title":"Autoencoding beyond pixels using a learned similarity metric","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Larsen","year":"2016"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1250\/ast.43.121"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3455008"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1250\/ast.41.761"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1250\/ast.42.140"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2014.09.003"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2016.09.001"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-68"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461332"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1424"},{"key":"ref62","first-page":"3165","article-title":"FastSpeech: Fast, robust and controllable text to speech","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ren","year":"2019"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053512"},{"key":"ref64","article-title":"Methods for Subjective Determination of Transmission Quality","year":"1996"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9970249\/10122591.pdf?arnumber=10122591","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T05:04:09Z","timestamp":1709269449000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10122591\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/taslp.2023.3275032","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}