{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:33:55Z","timestamp":1767339235813,"version":"3.46.0"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100020963","name":"Moonshot R&D","doi-asserted-by":"publisher","award":["JPMJPS2011"],"award-info":[{"award-number":["JPMJPS2011"]}],"id":[{"id":"10.13039\/501100020963","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,22]]},"DOI":"10.1109\/apsipaasc65261.2025.11249057","type":"proceedings-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:40:26Z","timestamp":1764355226000},"page":"903-908","source":"Crossref","is-referenced-by-count":1,"title":["Active Learning for Text-to-Speech Synthesis with Informative Sample Collection"],"prefix":"10.1109","author":[{"given":"Kentaro","family":"Seki","sequence":"first","affiliation":[{"name":"The University of Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinnosuke","family":"Takamichi","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takaaki","family":"Saeki","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hiroshi","family":"Saruwatari","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26488"},{"key":"ref3","article-title":"Naturalspeech 3: Zero-shot speech synthesis with factorized codec and diffusion models","author":"Ju","year":"2024","journal-title":"arXiv preprint"},{"journal-title":"JSUT corpus: free large-scale Japanese speech corpus for end-to-end speech synthesis","year":"2017","author":"Sonobe","key":"ref4"},{"journal-title":"JVS corpus: free Japanese multi-speaker voice corpus","year":"2019","author":"Takamichi","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1554"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87626-5_15"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095161"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1965"},{"journal-title":"JTubeSpeech: corpus of Japanese speech collected from YouTube for speech recognition and speaker verification","year":"2021","author":"Takamichi","key":"ref11"},{"key":"ref12","article-title":"J-CHAT: Japanese large-scale spoken dialogue corpus for spoken dialogue language modeling","author":"Nakata","year":"2024","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448068"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-12423-5_14"},{"article-title":"Active learning is a strong baseline for data subset selection","volume-title":"NeurIPS 2022 Workshop","author":"Park","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3472291"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60276-5_27"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLPRO.2025.3633089"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747345"},{"key":"ref21","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. NeurIPS","volume":"33","author":"Ho"},{"article-title":"Diffusion models are minimax optimal distribution estimators","volume-title":"Pcor. ICML","author":"Oko","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3261988"},{"volume-title":"ITA corpus","key":"ref24"},{"article-title":"FastSpeech 2: Fast and high-quality end-to-end text to speech","volume-title":"Proc. ICLR","author":"Ren","key":"ref25"},{"key":"ref26","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. NeurIPS","volume":"33","author":"Kong"},{"volume-title":"HiFi-GAN","key":"ref27"},{"volume-title":"FastSpeech 2-JSUT","key":"ref28"},{"volume-title":"x-vector","key":"ref29"}],"event":{"name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2025,10,22]]},"location":"Singapore, Singapore","end":{"date-parts":[[2025,10,24]]}},"container-title":["2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11248853\/11248968\/11249057.pdf?arnumber=11249057","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:07:58Z","timestamp":1764400078000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11249057\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc65261.2025.11249057","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}