A novel hybrid mandarin speech synthesis system using different base units for model training and concatenation

Ran Zhang, Jianhua Tao, Ya Li, Zhengqi Wen. A novel hybrid mandarin speech synthesis system using different base units for model training and concatenation. In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2014, Florence, Italy, May 4-9, 2014. pages 295-299, IEEE, 2014. [doi]

Authors

Ran Zhang

This author has not been identified. Look up 'Ran Zhang' in Google

Jianhua Tao

This author has not been identified. Look up 'Jianhua Tao' in Google

Ya Li

This author has not been identified. Look up 'Ya Li' in Google

Zhengqi Wen

This author has not been identified. Look up 'Zhengqi Wen' in Google