{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,29]],"date-time":"2025-01-29T05:27:02Z","timestamp":1738128422357,"version":"3.33.0"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"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":[[2024,12,3]]},"DOI":"10.1109\/apsipaasc63619.2025.10848766","type":"proceedings-article","created":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T18:37:05Z","timestamp":1738003025000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Analytic Study of Text-Free Speech Synthesis for Raw Audio using a Self-Supervised Learning Model"],"prefix":"10.1109","author":[{"given":"Joonyong","family":"Park","sequence":"first","affiliation":[{"name":"The University of Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daisuke","family":"Saito","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nobuaki","family":"Minematsu","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"A brief overview of unsupervised neural speech representation learning","author":"Borgholt","year":"2022","journal-title":"CoRR"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","year":"2020","author":"Ren","key":"ref3"},{"key":"ref4","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"Proceedings of the 38th International Conference on Machine Learning","volume":"139","author":"Kim"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref6","first-page":"1336","article-title":"On generative spoken language modeling from raw audio","volume":"9","author":"Lakhotia","year":"2021","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"ref7","article-title":"Representation learning with contrastive predictive coding","author":"Van den Oord","year":"2018","journal-title":"CoRR"},{"key":"ref8","first-page":"12449","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2743"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1755"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3206084"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746484"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10096797"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-2326"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"volume-title":"The lj speech dataset","year":"2017","author":"Ito","key":"ref18"},{"volume-title":"Reazonspeech: A free and massive corpus for Japanese ASR","year":"2023","author":"Yue","key":"ref19"},{"key":"ref20","article-title":"JSUT corpus: Free large-scale Japanese speech corpus for end-to-end speech synthesis","author":"Sonobe","year":"2017","journal-title":"CoRR"},{"key":"ref21","article-title":"JVS corpus: Free Japanese multi-speaker voice corpus","author":"Takamichi","year":"2019","journal-title":"CoRR"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2021-37"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-444"},{"volume-title":"Robust speech recognition via large-scale weak supervision","year":"2022","author":"Radford","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746250"},{"key":"ref26","first-page":"18003","article-title":"ContentVec: An improved self-supervised speech representation by disentangling speakers","volume-title":"Proceedings of the 39th International Conference on Machine Learning","author":"Qian"},{"key":"ref27","article-title":"JSSS: free japanese speech corpus for summarization and simplification","author":"Takamichi","year":"2020","journal-title":"CoRR"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054362"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1049\/sil2.12151"}],"event":{"name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2024,12,3]]},"location":"Macau, Macao","end":{"date-parts":[[2024,12,6]]}},"container-title":["2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10848542\/10848533\/10848766.pdf?arnumber=10848766","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,28]],"date-time":"2025-01-28T06:08:19Z","timestamp":1738044499000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10848766\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc63619.2025.10848766","relation":{},"subject":[],"published":{"date-parts":[[2024,12,3]]}}}