{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:30:40Z","timestamp":1775579440600,"version":"3.50.1"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10446960","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"10871-10875","source":"Crossref","is-referenced-by-count":5,"title":["FIRNet: Fundamental Frequency Controllable Fast Neural Vocoder With Trainable Finite Impulse Response Filter"],"prefix":"10.1109","author":[{"given":"Yamato","family":"Ohtani","sequence":"first","affiliation":[{"name":"National Institute of Information and Communications Technology,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takuma","family":"Okamoto","sequence":"additional","affiliation":[{"name":"National Institute of Information and Communications Technology,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomoki","family":"Toda","sequence":"additional","affiliation":[{"name":"National Institute of Information and Communications Technology,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hisashi","family":"Kawai","sequence":"additional","affiliation":[{"name":"National Institute of Information and Communications Technology,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1609.03499"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-314"},{"key":"ref3","first-page":"2415","article-title":"Efficient neural audio synthesis","volume-title":"Proc. ICML","author":"Kalchbrenner"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref5","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. NeurIPS","author":"Kong"},{"key":"ref6","article-title":"WaveGrad: Estimating gradients for waveform generation","volume-title":"Proc. ICLR","author":"Chen"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3275032"},{"key":"ref8","volume-title":"The Vowel","author":"Chiba","year":"1942"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3061245"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3051765"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095298"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414403"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2956145"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11130"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-912"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094872"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2023-33"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2016.09.001"},{"key":"ref20","first-page":"1043","article-title":"Mel-generalized cepstral analysis","volume-title":"Proc. ICASSP","author":"Tokuda"},{"key":"ref21","article-title":"Aperiodicity extraction and control using mixed mode excitation and group delay manipulation for a high quality speech analysis, modification and synthesis system STRAIGHT","author":"Kawahara","year":"2001","journal-title":"MAVEBA 2001"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01548"},{"key":"ref23","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref24","article-title":"Gaussian error linear units (gelus)","author":"Hendrycks","year":"2016"},{"key":"ref25","first-page":"2672","article-title":"Generative adversarial nets","volume-title":"Proc. NIPS","author":"Goodfellow"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.304"},{"key":"ref27","first-page":"14910","article-title":"MelGAN: Generative adversarial networks for conditional waveform synthesis","volume-title":"Proc. NeurIPS","author":"Kumar"},{"key":"ref28","article-title":"Hi-Fi-CAPTAIN: High-fidelity and high-capacity conversational speech synthesis corpus developed by NICT","author":"Okamoto","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-68"},{"key":"ref30","article-title":"SWIPE: A sawtooth waveform inspired pitch estimator for speech and music","volume-title":"Ph.D. Thesis, University of Florida","author":"Camacho","year":"2007"},{"key":"ref31","first-page":"495","article-title":"A Robust Algorithm for Pitch Tracking (RAPT)","volume-title":"chapter Speech Coding & Synthesis","author":"Talkin","year":"1995"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2014.09.003"},{"key":"ref33","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. ICLR","author":"Kingma"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-677"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10446960.pdf?arnumber=10446960","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:40:02Z","timestamp":1722573602000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446960\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446960","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}