Zobrazeno 1 - 10
of 41
pro vyhledávání: '"Shiyin Kang"'
Publikováno v:
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2809aab059742fa5205d6d5d119fa5f9
https://doi.org/10.1109/icassp49357.2023.10096785
https://doi.org/10.1109/icassp49357.2023.10096785
Publikováno v:
2022 IEEE Spoken Language Technology Workshop (SLT).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::85faca24f198fa230990b35bd98a1321
https://doi.org/10.1109/slt54892.2023.10022565
https://doi.org/10.1109/slt54892.2023.10022565
Publikováno v:
Interspeech 2022.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3889e53f43005d460cc44b53c506811d
https://doi.org/10.21437/interspeech.2022-131
https://doi.org/10.21437/interspeech.2022-131
Autor:
Helen Meng, Hui Lu, Yuewen Cao, Shiyin Kang, Xixin Wu, Xunying Liu, Zhiyong Wu, Songxiang Liu
Publikováno v:
IEEE/ACM Transactions on Audio, Speech, and Language Processing. 29:874-886
Expressive text-to-speech (E-TTS) synthesis is important for enhancing user experience in communication with machines using the speech modality. However, one of the challenges in E-TTS is the lack of a precise description of emotions. Previous catego
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d08213d049d9fc500b6b727fe708dba9
https://doi.org/10.1109/taslp.2021.3052688
https://doi.org/10.1109/taslp.2021.3052688
Publikováno v:
Neural Networks. 125:121-130
Attention based end-to-end speech synthesis achieves better performance in both prosody and quality compared to the conventional "front-end"-"back-end" structure. But training such end-to-end framework is usually time-consuming because of the use of
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::300b899ccbc6568433ececf0f24691da
https://doi.org/10.1016/j.neunet.2020.01.034
https://doi.org/10.1016/j.neunet.2020.01.034
Previous works on expressive speech synthesis focus on modelling the mono-scale style embedding from the current sentence or context, but the multi-scale nature of speaking style in human speech is neglected. In this paper, we propose a multi-scale s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::74c5a80eb719e89e6b36e95c8bd1a110
Previous works on expressive speech synthesis mainly focus on current sentence. The context in adjacent sentences is neglected, resulting in inflexible speaking style for the same text, which lacks speech variations. In this paper, we propose a hiera
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::dfd252d101fc31f2854460b48152f4dc
Publikováno v:
Interspeech 2021.
This paper describes a variational auto-encoder based non-autoregressive text-to-speech (VAENAR-TTS) model. The autoregressive TTS (AR-TTS) models based on the sequence-to-sequence architecture can generate high-quality speech, but their sequential d
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8189dd04bd542ee4818f81d70a2ca6e4
https://doi.org/10.21437/interspeech.2021-2121
https://doi.org/10.21437/interspeech.2021-2121
Publikováno v:
ICASSP
Text-to-speech systems now can generate speech that is hard to distinguish from human speech. In this paper, we propose the Huya multi-speaker and multi-style speech synthesis system which is based on DurIAN and HiFi-GAN to generate high-fidelity spe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2acccb472f3ab42a8f586e4571e36f16
https://doi.org/10.1109/icassp39728.2021.9414943
https://doi.org/10.1109/icassp39728.2021.9414943
Autor:
Peng Liu, Shiyin Kang, Songxiang Liu, Na Hu, Xunying Liu, Yuewen Cao, Dan Su, Helen Meng, Dong Yu
Publikováno v:
ISCSLP
State-of-the-art singing voice synthesis (SVS) models can generate natural singing voice of a target speaker, given his/her speaking/singing data in the same language. However, there may be challenging conditions where only speech data in a non-targe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b6e2e358797b0220b89d4ee6882c86f6
https://doi.org/10.1109/iscslp49672.2021.9362077
https://doi.org/10.1109/iscslp49672.2021.9362077