{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:37:03Z","timestamp":1767339423344,"version":"3.28.0"},"reference-count":45,"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\/icassp48485.2024.10448068","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"12351-12355","source":"Crossref","is-referenced-by-count":3,"title":["Diversity-Based Core-Set Selection for Text-to-Speech with Linguistic and Acoustic Features"],"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","article-title":"Neural voice cloning with a few samples","volume":"31","author":"Arik","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP49672.2021.9362069"},{"key":"ref4","first-page":"4693","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with tacotron","volume-title":"international conference on machine learning","author":"Skerry-Ryan"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095161"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1965"},{"key":"ref8","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":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRAIE51050.2020.9358310"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414403"},{"key":"ref11","article-title":"Active learning for convolutional neural networks: A core-set approach","author":"Sener","year":"2017","journal-title":"arXiv preprint arXiv:1708.00489"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(90)90011-W"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1313"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2567"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2190"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICSPCC55723.2022.9984283"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2688585"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/0304-3975(85)90224-5"},{"key":"ref19","article-title":"Fast greedy map inference for determinantal point process to improve recommendation diversity","volume":"31","author":"Chen","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref20","first-page":"152","article-title":"The use of mmr and diversity-based reranking in document reranking and summarization","volume-title":"Proceedings of the 14th Twente Workshop on Language Technology in Multimedia Information Retrieval","author":"Goldstein"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/1526709.1526761"},{"key":"ref22","first-page":"2","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proceedings of naacL-HLT","volume":"1","author":"Kenton"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref25","first-page":"12 449","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. NeurIPS","volume":"33","author":"Baevski"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2850935"},{"key":"ref27","article-title":"JVS corpus: Free Japanese multi-speaker voice corpus","author":"Takamichi","year":"2019","journal-title":"arXiv:1908.06248"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-755"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1584"},{"volume-title":"ITA corpus","key":"ref30"},{"article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","volume-title":"Proc. ICLR","author":"Ren","key":"ref31"},{"key":"ref32","first-page":"17 022","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":"ref33"},{"volume-title":"FastSpeech2 JSUT implementation","key":"ref34"},{"volume-title":"FastSpeech 2 - PyTorch Implementation","key":"ref35"},{"volume-title":"x-vector extractor for Japanese speech","key":"ref36"},{"article-title":"Line distilbert japanese","year":"2023","author":"\u201cKoga","key":"ref37"},{"volume-title":"bert-base-chinese","key":"ref38"},{"volume-title":"distilbert-base-uncased","key":"ref39"},{"volume-title":"wav2vec 2.0","key":"ref40"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-439"},{"volume-title":"UTMOS: UTokyo-SaruLab MOS Prediction System","key":"ref43"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-970"},{"key":"ref45","first-page":"28 492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. ICML","author":"Radford"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","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\/10448068.pdf?arnumber=10448068","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:36:02Z","timestamp":1722573362000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10448068\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10448068","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}