Intelligent retrieval of dynamic networked information from mobile terminals using spoken natural language queries

This paper presents a working architecture for intelligent retrieval of dynamic networked information from mobile terminals using spoken natural language queries. A very efficient dynamic keyword extraction technique is used to extract automatically limited numbers of keywords to specify the huge amount of networked information, so as to reduce the very difficult problem of recognizing unconstrained spoken natural language queries into the tractable task of spotting limited number of keywords embedded in the voice queries. A vocabulary-flexible voice keyword spotting technique is used to handle the live, dynamic and ever-changing networked information. A client-server architecture is used to integrate the dynamic keyword extraction and voice keyword spotter modules under a mobile network environment. Very encouraging experimental results indicating the feasibility of the proposed approach have been obtained.

[1]  Yumiko Matsuura,et al.  "Browse search using audio key-information" for multimedia on-demand systems , 1995 .

[2]  Michael Paterakis,et al.  On the voice-data integration in third generation wireless access communication networks , 1994, Eur. Trans. Telecommun..

[3]  Keh-Jiann Chen,et al.  Internet Chinese information retrieval using unconstrained Mandarin speech queries based on a client-server architecture and a PAT-tree-based language model , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[4]  Lee-Feng Chien,et al.  PAT-tree-based keyword extraction for Chinese information retrieval , 1997, SIGIR '97.

[5]  Karen Spärck Jones,et al.  Experiments in Spoken Document Retrieval , 1996, Inf. Process. Manag..

[6]  Gerard Salton,et al.  Automatic Text Processing: The Transformation, Analysis, and Retrieval of Information by Computer , 1989 .

[7]  T. Suda,et al.  Designing mobile computing systems using distributed objects , 1997 .

[8]  Lin-Shan Lee,et al.  Voice dictation of Mandarin Chinese , 1997, IEEE Signal Process. Mag..

[9]  Gaston H. Gonnet,et al.  New Indices for Text: Pat Trees and Pat Arrays , 1992, Information Retrieval: Data Structures & Algorithms.

[10]  Chiu-yu Tseng,et al.  A multi-phase approach for fast spotting of large vocabulary Chinese keywords from Mandarin speech using prosodic information , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[11]  Vijay Balasubramanian,et al.  Speech-Based Retrieval Using Semantic Co-Occurrence Filtering , 1994, HLT.

[12]  Victor Zue.  Navigating the Information Superhighway Using Spoken Language Interfaces , 1995, IEEE Expert.