{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T05:13:56Z","timestamp":1735103636939,"version":"3.32.0"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"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":[[2024,11,7]]},"DOI":"10.1109\/iscslp63861.2024.10800183","type":"proceedings-article","created":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T19:11:17Z","timestamp":1734981077000},"page":"601-605","source":"Crossref","is-referenced-by-count":0,"title":["Hola-TTS: A Cross-Lingual Zero-Shot Text-to-Speech System for Chinese, English, Japanese, and Korean"],"prefix":"10.1109","author":[{"given":"Hongwu","family":"Ding","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Anhui University,Hefei"}]},{"given":"Yiquan","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Software Engineering, Xi'an Jiaotong University,Xi'an"}]},{"given":"Wenyu","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Software Engineering, Xi'an Jiaotong University,Xi'an"}]},{"given":"JiaCheng","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Anhui University,Hefei"}]},{"given":"Jiaqi","family":"Mei","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Anhui University,Hefei"}]}],"member":"263","reference":[{"key":"ref1","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"International Conference on Machine Learning","author":"Kim","year":"2021"},{"key":"ref2","article-title":"Fastspeech: Fast, robust and controllable text to speech","volume":"32","author":"Ren","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref3","article-title":"Mega-tts: Zero-shot text-to-speech at scale with intrinsic inductive bias","author":"Jiang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","first-page":"2709","article-title":"Yourtts: Towards zero-shot multi-speaker tts and zero-shot voice conversion for everyone","volume-title":"International Conference on Machine Learning","author":"Casanova","year":"2022"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3362\/0262-8104.2002.009"},{"key":"ref6","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref7","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2022","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.673"},{"key":"ref9","article-title":"Speak foreign languages with your own voice: Cross-lingual neural codec language modeling","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2016"},{"key":"ref11","article-title":"Neural discrete representation learning","volume":"30","author":"Van Den Oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"issue":"8","key":"ref12","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.1109\/ISCSLP63861.2024.10800374","article-title":"Inspirational and Convincing Audio Generation Challenge 2024 ICAGC 2024","volume-title":"The 14th International Symposium on Chinese Spoken Language Processing (ISCSLP 2024)","author":"Fu","year":"2024"},{"key":"ref14","article-title":"Simple and controllable music generation","volume":"36","author":"Copet","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-78"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2017.8169987"},{"key":"ref17","article-title":"Cm3: A causal masked multimodal model of the internet","author":"Aghajanyan","year":"2022","journal-title":"arXiv preprint"},{"volume-title":"pengzhendong. g2pmix","year":"2024","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746682"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1965"},{"journal-title":"Reazonspeech: A free and massive corpus for japanese asr","year":"2016","author":"Fujimoto","key":"ref21"},{"volume-title":"jp1924. KoreaSpeech","year":"2024","key":"ref22"},{"key":"ref23","article-title":"Zipformer: A faster and better encoder for automatic speech recognition","volume-title":"The Twelfth International Conference on Learning Representations","author":"Yao","year":"2023"},{"key":"ref24","first-page":"17022","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"Kong","year":"2020","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","start":{"date-parts":[[2024,11,7]]},"location":"Beijing, China","end":{"date-parts":[[2024,11,10]]}},"container-title":["2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10799944\/10799969\/10800183.pdf?arnumber=10800183","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,24]],"date-time":"2024-12-24T06:26:17Z","timestamp":1735021577000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10800183\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,7]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/iscslp63861.2024.10800183","relation":{},"subject":[],"published":{"date-parts":[[2024,11,7]]}}}