Sciweavers

ICASSP
2010
IEEE

Non-parallel training for many-to-many eigenvoice conversion

13 years 10 months ago
Non-parallel training for many-to-many eigenvoice conversion
This paper presents a novel training method of an eigenvoice Gaussian mixture model (EV-GMM) effectively using non-parallel data sets for many-to-many eigenvoice conversion, which is a technique for converting an arbitrary source speaker’s voice into an arbitrary target speaker’s voice. In the proposed method, an initial EV-GMM is trained with the conventional method using parallel data sets consisting of a single reference speaker and multiple pre-stored speakers. Then, the initial EV-GMM is further refined using non-parallel data sets including a larger number of pre-stored speakers while considering the reference speaker’s voices as hidden variables. The experimental results demonstrate that the proposed method yields significant quality improvements in converted speech by enabling us to use data of a larger number of pre-stored speakers.
Yamato Ohtani, Tomoki Toda, Hiroshi Saruwatari, Ki
Added 06 Dec 2010
Updated 06 Dec 2010
Type Conference
Year 2010
Where ICASSP
Authors Yamato Ohtani, Tomoki Toda, Hiroshi Saruwatari, Kiyohiro Shikano
Comments (0)