Topic extraction based on continuous speech recognition in broadcast-news speech

The paper reports on topic extraction in Japanese broadcast news speech. We studied, using continuous speech recognition, the extraction of several topic words from broadcast news. A combination of multiple topic words represents the content of the news. This is more detailed and more flexible than a single word or a single category. A topic extraction model shows the degree of relevance between each topic word and each word in the articles. For all words in an article, topic words which have high total relevance score are extracted from the article. We trained the topic extraction model with five years of newspapers, using the frequency of topic words taken from headlines and words in articles. The degree of relevance between topic words and words in articles is calculated on the basis of statistical measures, i.e., mutual information or the /spl chi//sup 2/ value. In topic extraction experiments for recognized broadcast news speech, we extracted five topic words using a /spl chi//sup 2/ based model and found that 75% of them agreed with topic words chosen by subjects.

[1]  Katsuhiko Shirai,et al.  Toward automatic transcription of Japanese broadcast news , 1997, EUROSPEECH.

[2]  Herbert Gish,et al.  Issues in topic identification on the switchboard corpus , 1994, ICSLP.

[3]  Richard M. Schwartz,et al.  Improved topic discrimination of broadcast news using a model of multiple simultaneous topics , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[4]  Steve J. Young,et al.  Tree-Based State Tying for High Accuracy Modelling , 1994, HLT.

[5]  Slava M. Katz,et al.  Estimation of probabilities from sparse data for the language model component of a speech recognizer , 1987, IEEE Trans. Acoust. Speech Signal Process..

[6]  Richard P. Lippmann,et al.  Techniques for information retrieval from voice messages , 1991, [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing.

[7]  Takeshi Mori,et al.  Japanese large-vocabulary continuous-speech recognition using a business-newspaper corpus , 1996, Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96.

[8]  Damaris M. Ayuso,et al.  Gisting conversational speech , 1992, [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[9]  David A. James,et al.  A system for unrestricted topic retrieval from radio news broadcasts , 1996, 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings.

[10]  Karen Spärck Jones,et al.  Talker-independent keyword spotting for information retrieval , 1995, EUROSPEECH.

[11]  Herbert Gish,et al.  Spotting events in continuous speech , 1994, Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing.

[12]  Sean Connolly,et al.  Improvements in switchboard recognition and topic identification , 1996, 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings.