No abstract

This 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 o f relevance between each topic-word and each word in the articles. For all walrds in a n 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 o f statistical measures, i.e., mutual information or the X*-value. In topic-extraction experiments for recognized broadcast-news speech, we extracted five topic-words using a X2-based model and found that 75% of them agreed with topic-words chosen by subjects.

No abstract

This paper describes an automatic content indexing system for news programs, with a special emphasis on its segmentation process. The process can successfully segment an entire news program into topic-centered news stories; the primary tool is a linguistic topic segmentation algorithm. Experiments show that the resulting speech-based segments are fairly accurate, and scene change points supplied by an external video processor can be of help in improving segmentation effectiveness.

This paper reports on topic extraction in Japanese broadcastnews speech. We studied, using continuous speech recognition, the extraction of several topic-words h m broadcast-news. A combination of multiple topic-words represents the content of the news. This is a more detailed and more flexible approach than using 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 article. For all words in an article, topic-words which have high total relevance score are extracted. We trained the topicextraction model with five years of newspapers, using the frequency of topic-words taken f " 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 X2-value. In topicextraction experiments for recognized broadcast-news speech, we extracted five topic-words h m the IO-best hypotheses using a X2-based model and found that 76.6% of them agreed with the topic-words chosen by subjects.