Speech synthesis software with variable speaking rate and its implementation on a 32-bit microprocessor
T. Ebihara, Y. Ishikawa, Y. Kisuki, T. Sakamoto, T. Hase · 2002
We proposed a speech synthesis method with variable speaking rate based on phoneme duration features of natural speech. The real-time synthesis software required 8 MIPS CPU power was achieved on a 32-bit microprocessor.