{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T20:46:52Z","timestamp":1778705212496,"version":"3.51.4"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100020962","name":"ACT-X","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100020962","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,2]]},"DOI":"10.1109\/slt61566.2024.10832155","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:27Z","timestamp":1737052287000},"page":"750-757","source":"Crossref","is-referenced-by-count":3,"title":["Cross-Dialect Text-to-Speech In Pitch-Accent Language Incorporating Multi-Dialect Phoneme-Level Bert"],"prefix":"10.1109","author":[{"given":"Kazuki","family":"Yamauchi","sequence":"first","affiliation":[{"name":"The University of Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuki","family":"Saito","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.1988.196677"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414226"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097074"},{"key":"ref4","first-page":"4693","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with Tacotron","volume-title":"Proc. ICML","author":"Skerry-Ryan"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683501"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2571"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-367"},{"key":"ref8","article-title":"Auto-encoding variational Bayes","volume-title":"Proc. ICLR","author":"Kingma"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-0601-3_17"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/ssw.2021-33"},{"key":"ref11","first-page":"6309","article-title":"Neural discrete representation learning","volume-title":"Proc. NIPS","author":"van den Oord"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1757"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3190672"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPAASC55919.2022.9979876"},{"key":"ref15","first-page":"434","article-title":"CPJD Corpus: Crowdsourced parallel speech corpus of Japanese dialects","volume-title":"Proc. LREC","author":"Takamichi"},{"key":"ref16","first-page":"112","article-title":"LLM-based MT data creation: Dialectal to MSA translation shared task","volume-title":"Proc. OSACT Workshop","author":"Abdelaziz"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1250\/ast.41.761"},{"key":"ref18","article-title":"JMD: Japanese multi-dialect corpus","author":"Takamichi","year":"2021"},{"key":"ref19","first-page":"28 492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.2001-396"},{"key":"ref21","article-title":"FastSpeech 2: Fast and high-quality end-to-end text to speech","volume-title":"Proc. ICLR","author":"Ren"},{"key":"ref22","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. NeurIPS, Virtual Conference","author":"Kong"},{"key":"ref23","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint arXiv:2307.09288"},{"key":"ref24","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. ICLR","author":"Kingma"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref27","first-page":"311","article-title":"BLEU: A method for automatic evaluation of machine translation","volume-title":"Proc. ACL","author":"Papineni"},{"key":"ref28","article-title":"BERTScore: Evaluating text generation with BERT","volume-title":"Proc. ICLR, Virtual Conference","author":"Zhang"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2070"}],"event":{"name":"2024 IEEE Spoken Language Technology Workshop (SLT)","location":"Macao","start":{"date-parts":[[2024,12,2]]},"end":{"date-parts":[[2024,12,5]]}},"container-title":["2024 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10830790\/10830793\/10832155.pdf?arnumber=10832155","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,20]],"date-time":"2025-01-20T18:39:24Z","timestamp":1737398364000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832155\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/slt61566.2024.10832155","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]}}}