{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T05:47:41Z","timestamp":1767332861082,"version":"3.48.0"},"reference-count":51,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100000646","name":"Japan Society for the Promotion of Science (JSPS) KAKENHI","doi-asserted-by":"publisher","award":["22H03639"],"award-info":[{"award-number":["22H03639"]}],"id":[{"id":"10.13039\/501100000646","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000646","name":"Japan Society for the Promotion of Science (JSPS) KAKENHI","doi-asserted-by":"publisher","award":["24KJ0860"],"award-info":[{"award-number":["24KJ0860"]}],"id":[{"id":"10.13039\/501100000646","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100020963","name":"Moonshot Research and Development","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":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3645005","type":"journal-article","created":{"date-parts":[[2025,12,17]],"date-time":"2025-12-17T18:47:51Z","timestamp":1765997271000},"page":"217900-217912","source":"Crossref","is-referenced-by-count":0,"title":["Toward Data-Efficient Speech Synthesis: Active Learning-Based Corpus Construction for Multi-Speaker Text-to-Speech Synthesis"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-2566-2648","authenticated-orcid":false,"given":"Kentaro","family":"Seki","sequence":"first","affiliation":[{"name":"Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7967-2613","authenticated-orcid":false,"given":"Yuki","family":"Saito","sequence":"additional","affiliation":[{"name":"Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0520-7847","authenticated-orcid":false,"given":"Shinnosuke","family":"Takamichi","sequence":"additional","affiliation":[{"name":"Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takaaki","family":"Saeki","sequence":"additional","affiliation":[{"name":"Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0876-5617","authenticated-orcid":false,"given":"Hiroshi","family":"Saruwatari","sequence":"additional","affiliation":[{"name":"Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref3","first-page":"8067","article-title":"Glow-TTS: A generative flow for text-to-speech via monotonic alignment search","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kim"},{"key":"ref4","first-page":"1","article-title":"FastSpeech 2: Fast and high-quality end-to-end text to speech","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Ren"},{"key":"ref5","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"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448291"},{"key":"ref7","first-page":"22605","article-title":"NaturalSpeech 3: Zero-shot speech synthesis with factorized codec and diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ju"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3356232"},{"key":"ref9","article-title":"Towards human-like spoken dialogue generation between AI agents from written dialogue","author":"Mitsui","year":"2023","journal-title":"arXiv:2310.01088"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.1055"},{"key":"ref11","article-title":"Moshi: A speech-text foundation model for real-time dialogue","author":"D\u00e9fossez","year":"2024","journal-title":"arXiv:2410.00037"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1965"},{"key":"ref13","article-title":"JTubeSpeech: Corpus of Japanese speech collected from YouTube for speech recognition and speaker verification","author":"Takamichi","year":"2021","journal-title":"arXiv:2112.09323"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095161"},{"key":"ref15","article-title":"J-CHAT: Japanese large-scale spoken dialogue corpus for spoken dialogue language modeling","author":"Nakata","year":"2024","journal-title":"arXiv:2407.15828"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832365"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448068"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLPRO.2025.3633089"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC65261.2025.11249057"},{"article-title":"Superseded-CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit","year":"2016","author":"Veaux","key":"ref20"},{"journal-title":"The Lj Speech Dataset","year":"2017","author":"Ito","key":"ref21"},{"key":"ref22","article-title":"JSUT corpus: Free largescale Japanese speech corpus for end-to-end speech synthesis","author":"Sonobe","year":"2017","journal-title":"arXiv:1711.00354"},{"key":"ref23","article-title":"JVS corpus: Free Japanese multi-speaker voice corpus","author":"Takamichi","year":"2019","journal-title":"arXiv:1908.06248"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2441"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-502"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639642"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-37"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2567"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3472291"},{"key":"ref31","article-title":"A survey on data selection for language models","author":"Albalak","year":"2024","journal-title":"arXiv:2402.16827"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3711118"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2014.6889457"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/11871842_40"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206627"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0781-x"},{"key":"ref37","article-title":"Active learning for convolutional neural networks: A core-set approach","author":"Sener","year":"2017","journal-title":"arXiv:1708.00489"},{"key":"ref38","first-page":"1183","article-title":"Deep Bayesian active learning with image data","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gal"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2002.5745510"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.848882"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2009.03.004"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2316"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9533839"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TASLPRO.2025.3565216"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3582395"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60276-5_27"},{"key":"ref48","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"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-439"},{"issue":"86","key":"ref50","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096956"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11301677.pdf?arnumber=11301677","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T05:44:01Z","timestamp":1767332641000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11301677\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3645005","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2025]]}}}