{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T06:51:28Z","timestamp":1764399088071,"version":"3.46.0"},"reference-count":27,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,22]]},"DOI":"10.1109\/apsipaasc65261.2025.11249200","type":"proceedings-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:40:26Z","timestamp":1764355226000},"page":"765-770","source":"Crossref","is-referenced-by-count":0,"title":["MixedG2P-T5: G2P-Free Speech Synthesis for Mixed-Script Texts Using Speech Self-Supervised Learning and Language 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","volume":"abs\/2203.01829","author":"Borgholt","year":"2022","journal-title":"CoRR"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref3","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","year":"2021"},{"key":"ref4","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":"ref5","first-page":"1244912460","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":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-334"},{"key":"ref8","first-page":"1134","article-title":"Reazonspeech: A free and massive corpus for Japanese ASR","volume-title":"Proceedings of Annual Meeting of the Association for NLP","author":"Yue","year":"2023"},{"issue":"140","key":"ref9","first-page":"1140","article-title":"Exploring the limits of transfer learning with a unified text-totext transformer","volume":"21","author":"Raffel","year":"2019","journal-title":"J. Mach. Learn. Res."},{"key":"ref10","article-title":"JSUT corpus: Free large-scale Japanese speech corpus for end-to-end speech synthesis","volume":"abs\/1711.00354","author":"Sonobe","year":"2017","journal-title":"CoRR"},{"key":"ref11","article-title":"JVS corpus: Free Japanese multispeaker voice corpus","volume":"abs\/1908.06248","author":"Takamichi","year":"2019","journal-title":"CoRR"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2021-37"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-444"},{"key":"ref14","article-title":"JSSS: free japanese speech corpus for summarization and simplification","volume":"abs\/2010.01793","author":"Takamichi","year":"2020","journal-title":"CoRR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-546"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.393"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3176"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.sigmorphon-1.16"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-538"},{"key":"ref20","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","year":"2022"},{"key":"ref21","volume":"abs\/2006.04558","author":"Ren","year":"2020","journal-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech"},{"volume-title":"Robust speech recognition via largescale weak supervision","year":"2022","author":"Radford","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-439"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1049\/sil2.12151"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.41"},{"key":"ref27","first-page":"5206","article-title":"ByT5: Towards a token-free future with pre-trained byte-to-byte models","author":"Linting","year":"2021","journal-title":"TACL 2022"}],"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\/11249200.pdf?arnumber=11249200","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T06:50:36Z","timestamp":1764399036000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11249200\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc65261.2025.11249200","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}