{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:28:44Z","timestamp":1774420124075,"version":"3.50.1"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10887607","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Mora-Level Prosody Prediction for Text-to-Speech Using Japanese BERT Without Accentual Labels"],"prefix":"10.1109","author":[{"given":"Tadashi","family":"Ogura","sequence":"first","affiliation":[{"name":"National Institute of Information and Communications Technology,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takuma","family":"Okamoto","sequence":"additional","affiliation":[{"name":"National Institute of Information and Communications Technology,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yamato","family":"Ohtani","sequence":"additional","affiliation":[{"name":"National Institute of Information and Communications Technology,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Erica","family":"Cooper","sequence":"additional","affiliation":[{"name":"National Institute of Information and Communications Technology,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomoki","family":"Toda","sequence":"additional","affiliation":[{"name":"Nagoya University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hisashi","family":"Kawai","sequence":"additional","affiliation":[{"name":"National Institute of Information and Communications Technology,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":"FastSpeech 2: Fast and high-quality end-to-end text to speech","volume-title":"Proc. ICLR","author":"Ren"},{"key":"ref3","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"Proc. ICML","author":"Kim"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10294"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446890"},{"key":"ref6","article-title":"NaturalSpeech 2: Latent diffusion models are natural and zero-shot speech and singing synthesizers","volume-title":"Proc. ICLR","author":"Shen"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref8","first-page":"4171","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL-HLT","author":"Devlin"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3177"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054337"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1430"},{"key":"ref12","first-page":"2958","article-title":"Improving prosody modelling with cross-utterance BERT embeddings for end-toend speech synthesis","volume-title":"Proc. ICASSP","author":"Xu"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1757"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3348762"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682353"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2020EDP7104"},{"key":"ref17","first-page":"1","article-title":"Japanese dialects and general linguistics","volume":"148","author":"Kubozono","year":"2015","journal-title":"J. Linguist. Soc. Jpn."},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054081"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-914"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSPW62465.2024.10626112"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-708"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3190672"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682816"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.67"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.294"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.632"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1121\/1.4919349"},{"key":"ref28","first-page":"8067","article-title":"Glow-TTS: A generative flow for text-to-speech via monotonic alignment search","volume-title":"Proc. NeurIPS","author":"Kim"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/icassp39728.2021.9413889"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414858"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2504"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747707"},{"key":"ref33","article-title":"ESPnet2-TTS: Extending the edge of TTS research","author":"Hayashi","year":"2021"},{"key":"ref34","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. NeurIPS","author":"Paszke"},{"key":"ref35","article-title":"Hi-Fi-CAPTAIN: High-fidelity and high-capacity conversational speech synthesis corpus developed by NICT","author":"Okamoto","year":"2023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-68"},{"key":"ref37","first-page":"8382","article-title":"MMDAgent\u2014A fully open-source toolkit for voice tnteraction systems","volume-title":"Proc. ICASSP","author":"Lee"},{"key":"ref38","first-page":"997","article-title":"Mobile PresenTra: NICT fast neural text-to-speech system on smartphones with incremental inference of MS-FC-HiFi-GAN for low-latency synthesis","volume-title":"Proc. Interspeech","author":"Okamoto"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3366707"},{"key":"ref40","article-title":"Decoupled weight decay regularization","volume-title":"Proc. ICLR","author":"Loshchilov"},{"key":"ref41","first-page":"7","article-title":"Corpus of spontaneous Japanese: Its design and evaluation","volume-title":"Proc. SSPR","author":"Maekawa"},{"key":"ref42","year":"1996","journal-title":"Methods for subjective determination of transmission quality"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1250\/ast.41.761"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1525\/9780520940420-020"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10887607.pdf?arnumber=10887607","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:31Z","timestamp":1774416391000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10887607\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10887607","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}