A New Syllable-Based Approach for Retrieving Mandarin Spoken Documents Using Short Speech Queries

Intelligent and efficient information retrieval techniques allowing easy access to huge amount and various types of information become highly desired and have been extensively studied in recent years. Considering the fast growth of audio resources and the characteristic monosyllabic structure of the Chinese language, a syllable-based framework of retrieving Mandarin spoken documents using speech queries has been investigated. This paper presents a new syllable-based approach that is based on matching the whole syllable lattice directly instead of using the syllable or syllable pair information extracted from the syllable lattice. The experimental results show that the retrieval performance can be significantly improved.