A spoken-access approach for chinese text and speech information retrieval

Abstract

This paper presents an efficient spoken access approach for both Chinese text and Mandarin speech information retrieval. The proposed approach is developed not only to deal with the retrieval of spoken documents, but also to improve the capability of human-computer interaction via voice input for information retrieval systems. Based on utilization of the mono-syllabic structure of the Chinese language, the proposed approach can tolerate speech recognition errors by performing speech query recognition and approximate information retrieval at the syllable-level. Furthermore, with the help of automatic term suggestion and relevance feedback techniques, the proposed approach is robust in allowing users using voice input to interact with IR systems at each stage of the retrieval process. Extensive experiments show that the proposed approach can improve the effectiveness of information retrieval via speech interaction. The encouraging results suggest that a Mandarin speech interface for information retrieval and digital library systems can, therefore, be developed.

Written versus spoken queries: A qualitative and quantitative comparative analysis

“…• A vocal dialogue manager can make interaction between IR system and user more natural and effective, encouraging the use of techniques like relevance feedback and results browsing, as shown in (Chien et al, 2000).…”

“…It involves the integration of an ASR system and an IR system, and is not "simply connected by way of an input/output protocol" to an IR system (Fujii et al, 2002). This view was taken by (Chien, Wang, Bai, & Li, 2000) who built an efficient spoken-access approach for both Chinese text and Mandarin speech information retrieval, enabling users to submit spoken queries in an interactive way. The extensive experimentation reported in this paper shows that speech interaction can improve the effectiveness of information retrieval.…”

Query expansion using phonetic confusions for Chinese spoken document retrieval

“…The approach has been adopted by Ng et al [4] By virtue of the syllabic nature of the Chinese language, the syllable seems to be a suitable sub-word unit for indexing spoken documents. Wang et al [5] and Meng et al [6] have used the syllable-based approach for indexing spoken documents in two Chinese dialects -Mandarin and Cantonese. This work extends the study reported in [6], where textual queries are used to retrieve Cantonese spoken documents.…”

Spoken document retrieval for the languages of Hong Kong

“…Other previous work in this area include: Mandarin spoken document retrieval by [Chien et al, 1999] and ; and the Informedia Project from CMU [Wactlar et al, 1996] which indexed audio tracks of news broadcasts with largevocabulary speech recognition and demonstrated multilingual capability in handling English and SerboCroatian.…”