The Research Of Mongolian Speech Synthetical Technology

According to the development of Network and Multimedia technology, the sound technology developed much in context. Speech Synthesis System is also called Text-To-Speech system. Its main function is converting text file to wave file, which make the computer not only deal with data, picture and letter, but also can speak like man. Since 1990, TTS System of French, German, English and Japanese based on PSOLA successfully developed. Chinese TTS system is also in use.Mongolian is the official language of Inner Mongolia Autonomous Region, and above three hundred thousand Mongolian uses it in daily life. So the research is worth, and the meaning is great to Mongolian's information industry. In the system, we use the waveform concatenation method and PSOLA, developed the Mongolian Text-To-Speech acoustic inventory and corpus. The study work is going on.