KEYWORD SPOTTING IN BROADCAST NEWS

In this presentation, we introduce several research topics related with the keyword spotting system on broadcast news. The system searches the keyword speech in online broadcast news and extracts the articles including the keyword(s). To obtain a stable recognition performance, the system uses several speech processing techniques such as utterance verification, out-of-vocabulary rejection, audio classification, and noise reduction. We will show an overall configuration for our system and report technical advances as well as some experimental results. We also describe future works for the system improvements and the application for further complicate spoken documents like interviews or movies.

[1]  David Anthony James,et al.  The Application of Classical Informa - tion Retrieval Techniques to Spoken Documents , 1995 .

[2]  Ren-Hua Wang,et al.  A comparative study on various confidence measures in large vocabulary speech recognition , 2004, 2004 International Symposium on Chinese Spoken Language Processing.

[3]  Aaron E. Rosenberg,et al.  Performance tradeoffs in dynamic time warping algorithms for isolated word recognition , 1980 .

[4]  Hui Jiang,et al.  Confidence measures for speech recognition: A survey , 2005, Speech Commun..

[5]  Joseph Picone,et al.  Applications of support vector machines to speech recognition , 2004, IEEE Transactions on Signal Processing.

[6]  A. Gray,et al.  Distance measures for speech processing , 1976 .

[7]  Jean-Luc Gauvain,et al.  The LIMSI Broadcast News transcription system , 2002, Speech Commun..

[8]  Karen Spärck Jones,et al.  Automatic content-based retrieval of broadcast news , 1995, MULTIMEDIA '95.

[9]  L. Liao,et al.  Algorithms for speech classification , 1999, ISSPA '99. Proceedings of the Fifth International Symposium on Signal Processing and its Applications (IEEE Cat. No.99EX359).