A multilingual text-to-speech system

An MITalk-based real-time system for unrestricted English, Japanese, and Chinese text-to-speech synthesis has been developed with high observed intelligibility (94% for word recognition in English and 70.8% for 119 Japanese monosyllables). The approach in making the system multilingual has been simple yet effective: in developing the Japanese and Chinese systems, the authors have used the hardware and the program structure and tools of the system originally developed for English, but have otherwise kept the development of the different languages separate. In addition to substantial improvements and modifications of the original MITalk, two major innovations in the system are (1) the method for controlling the glottal pulse and (2) the Phoenix development tools, which combine a powerful and flexible parameter editor with programs for acoustic analysis.<<ETX>>