Speech corpus script design for TTS system applied on railway passenger service information broadcasting

An approach of speech corpus script design for a s customized TTS engine that is applied on railway passenger service information broadcasting is presented in this paper. Raw text material is collected according to railway service information classification. A modified greedy algorithm is proposed to generate an optimal corpus script based on the statistics of prosodic nature of the raw corpus. A customized TTS engine is built by using the designed corpus script. The engine is applied on a railway passenger service information broadcasting system. Perceptual evaluation of the system prototype shows satisfactory performance. The script design focuses on Chinese.