Multimodal voice conversion based on non-negative matrix factorization

Kenta Masaka, Ryo Aihara, Tetsuya Takiguchi, Yasuo Ariki. Multimodal voice conversion based on non-negative matrix factorization. EURASIP J. Audio, Speech and Music Processing, 2015:24, 2015. [doi]

Authors

Kenta Masaka

This author has not been identified. Look up 'Kenta Masaka' in Google

Ryo Aihara

This author has not been identified. Look up 'Ryo Aihara' in Google

Tetsuya Takiguchi

This author has not been identified. Look up 'Tetsuya Takiguchi' in Google

Yasuo Ariki

This author has not been identified. Look up 'Yasuo Ariki' in Google