Speech synthesis method based on application-specific synthetic units and its implementation on a 32-bit microprocessor

A novel speech synthesis algorithm with application-specific synthesis units has been implemented in an embedded MCU. This method approximately halves the required amount of memory, making high-quality synthetic speech available in many kinds of electronic equipment.

[1]  Yoshinori Sagisaka,et al.  Concatenative speech synthesis by minimum distortion criteria , 1992, [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[2]  Hideyuki Mizuno,et al.  A new Japanese text-to-speech synthesizer based on COC synthesis method , 1990, ICSLP.

[3]  Shigeru Katagiri,et al.  A large-scale Japanese speech database , 1990, ICSLP.

[4]  T. Sakamoto,et al.  Speech Synthesis Software For A 32-bit Microprocessor , 1998, International 1998 Conference on Consumer Electronics.