LARGE-VOCABULARY CHINESE TEXT/SPEECH INFORMATION RETRIEVAL USING MANDARIN SPEECH QUERIES

The network technology and the Internet are creating a completely new information era. It is believed that in the near future numerous of digital libraries and a great variety of multimedia databases, which consist of heterogeneous types of information including text, audio, image, video and so on, will be available worldwide via the Internet. This paper deals with the problem of Chinese text and Mandarin speech information retrieval with Mandarin speech queries. Instead of using the syllable-based information alone, the word-based information was also successfully incorporated to further improve the retrieving performance. A prototype system with an interface supporting some user-friendly functions was successfully implemented and the initial test results verified the feasibility of our approaches.