Mandarin spoken document retrieval based on syllable lattice matching

摘要

Spoken document retrieval (SDR) has been extensively studied in recent years because of its potential use in navigating large multi-media collections in the near future. Considering the characteristics and monosyllabic structure of the Chinese language, a syllable-based framework for 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 and syllable-pair information extracted from the syllable lattice. The experimental results show that the retrieval performance can be improved significantly.