Realization of improved HMM-based speech synthesis system

This paper focuses research on the key technology of speech synthesis system based on HMM (Hidden Markov Model). With the help of HTK and Festival, three English sentences are synthesized. To improve the effect of HMM, a definition of label sequence format is described in detail. According to the definition, the results of this system are obtained. From the waveforms of the synthesized speech and the listening test, the synthesized speech is clear, understandable and naturally.

[1]  Keiichi Tokuda,et al.  Speech parameter generation algorithms for HMM-based speech synthesis , 2000, 2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100).

[2]  Paul Taylor,et al.  Festival Speech Synthesis System , 1998 .

[3]  Keiichi Tokuda,et al.  Simultaneous modeling of spectrum, pitch and duration in HMM-based speech synthesis , 1999, EUROSPEECH.

[4]  Keiichi Tokuda,et al.  Hidden Markov models based on multi-space probability distribution for pitch pattern modeling , 1999, 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258).

[5]  Wu Bao-min.  HMM-Based English Text-to-Speech System , 2008 .

[6]  Wu Yi-jian.  HMM-based Trainable Speech Synthesis for Chinese , 2006 .