5th International Conference on Spoken Language Processing

Sydney, Australia
November 30 - December 4, 1998

Indexing and Classification of TV News Articles Based on Speech Dictation Using Word Bigram

Jun Ogata, Yasuo Ariki

Ryukoku University, Japan

In order to construct a news database with a function of video on demand (VOD), it is required to classify news articles into topics. In this paper, we propose a method to automatically index and classify TV news articles into 10 topics based on a speech dictation techniques using speaker independent triphone HMMs and word bigram.

Full Paper

Bibliographic reference.  Ogata, Jun / Ariki, Yasuo (1998): "Indexing and classification of TV news articles based on speech dictation using word bigram", In ICSLP-1998, paper 0126.