Zobrazeno 1 - 3
of 3
pro vyhledávání: '"Huaizhen Tang"'
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_________::0dd8b4d07699438f90a1928b2760918f
https://doi.org/10.1109/icassp49357.2023.10094969
https://doi.org/10.1109/icassp49357.2023.10094969
Autor:
SiCheng Yang, Methawee Tantrawenith, Haolin Zhuang, Zhiyong Wu, Aolan Sun, Jianzong Wang, Ning Cheng, Huaizhen Tang, Xintao Zhao, Jie Wang, Helen Meng
One-shot voice conversion (VC) with only a single target speaker's speech for reference has become a hot research topic. Existing works generally disentangle timbre, while information about pitch, rhythm and content is still mixed together. To perfor
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::593906cbc458219c0d64c93c0493aced
http://arxiv.org/abs/2208.08757
http://arxiv.org/abs/2208.08757
Non-parallel many-to-many voice conversion remains an interesting but challenging speech processing task. Recently, AutoVC, a conditional autoencoder based method, achieved excellent conversion results by disentangling the speaker identity and the sp
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f8eb6add10416e1a079d6b6b768dd71d
http://arxiv.org/abs/2208.04035
http://arxiv.org/abs/2208.04035