{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T07:09:14Z","timestamp":1775200154244,"version":"3.50.1"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"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":[[2025,12,6]]},"DOI":"10.1109\/asru65441.2025.11434739","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-4","source":"Crossref","is-referenced-by-count":0,"title":["Voice Factor Control Using FIR-Based Fast Neural Vocoder for Speech Generation Applications"],"prefix":"10.1109","author":[{"given":"Yamato","family":"Ohtani","sequence":"first","affiliation":[{"name":"National Institute of Information and Communications Technology,Japan"}]},{"given":"Takuma","family":"Okamoto","sequence":"additional","affiliation":[{"name":"National Institute of Information and Communications Technology,Japan"}]},{"given":"Tomoki","family":"Toda","sequence":"additional","affiliation":[{"name":"Nagoya University,Japan"}]},{"given":"Hisashi","family":"Kawai","sequence":"additional","affiliation":[{"name":"National Institute of Information and Communications Technology,Japan"}]}],"member":"263","reference":[{"key":"ref1","article-title":"FastSpeech 2: Fast and high-quality end-to-end text to speech","volume-title":"Proc. ICLR","author":"Ren"},{"key":"ref2","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"Proc. ICML","author":"Kim"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10294"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446890"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2518"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2023-14"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-947"},{"key":"ref8","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","volume-title":"Proc. ICML","author":"Wang"},{"key":"ref9","first-page":"6184","article-title":"Zero-shot multi-speaker text-to-speech with state-of-theart neural speaker embeddings","volume-title":"Proc. ICASSP 2020","author":"Cooper"},{"key":"ref10","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023","journal-title":"arXiv"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/icassp39728.2021.9413889"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096480"},{"key":"ref13","article-title":"PITS: Variational pitch inference without fundamental frequency for end-to-end pitchcontrollable TTS","volume-title":"ICML 2023 Workshop on Structured Probabilistic Inference & Generative Modeling","author":"Lee"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448173"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1093\/ietisy\/e90-d.5.825"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639215"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref18","volume-title":"The Vowel","author":"Chiba","year":"1942"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLPRO.2025.3564048"},{"key":"ref20","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","volume-title":"MAVEBA 2001","author":"Kawahara","year":"2001"},{"key":"ref21","first-page":"1043","article-title":"Mel-generalized cepstral analysis","volume-title":"Proc. ICASSP","author":"Tokuda"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2014.09.003"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2016.09.001"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2023-33"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1972.8727"},{"key":"ref26","volume-title":"Hi-Fi-CAPTAIN: High-fidelity and high-capacity conversational speech synthesis corpus developed by NICT","author":"Okamoto","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-646"},{"key":"ref28","first-page":"997","article-title":"Mobile PresenTra: NICT fast neural text-to-speech system on smartphones with incremental inference of ms-fc-hifi-gan for law-latency synthesis","volume-title":"Proc. INTERSPEECH 2024","author":"Okamoto"},{"key":"ref29","first-page":"8067","article-title":"Glow-TTS: A generative flow for text-to-speech via monotonic alignment search","volume-title":"Proc. NeurIPS","author":"Kim"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01548"}],"event":{"name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,12,6]]},"end":{"date-parts":[[2025,12,10]]}},"container-title":["2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11434577\/11433836\/11434739.pdf?arnumber=11434739","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:59:11Z","timestamp":1775192351000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434739\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434739","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}