Title :
Segmentation and classification of TV news articles based on speech dictation
Author :
Takao, S. ; Ariki, Y. ; Ogata, J.
Author_Institution :
Dept. of Electron. & Inf., Ryukoku Univ., Ohtsu, Japan
Abstract :
We propose a method to automatically segment continuous TV news speech into articles and classify them into 10 topics based on speech dictation techniques using speaker independent triphone HMMs and word bigram. The proposed method is composed of keyword selection and topic function which computes the similarity between topics and the analytical period in spoken sentences. In the keyword selection, relative mutual information is proposed and compared with other 5 measures. It showed the highest score 81.8% and 87.0% in topic classification and topic boundary detection respectively. In the topic function, we compared four methods and the normalized association showed the best scores in topic segmentation and classification
Keywords :
dictation; information theory; signal classification; speech processing; television broadcasting; TV broadcasting; TV news articles classification; TV news articles segmentation; analytical period; automatic segmentation; continuous TV news speech; keyword selection; normalized association; relative mutual information; speaker independent triphone HMM; speech dictation; spoken sentences; topic boundary detection; topic classification; topic function; topic segmentation; topic similarity; word bigram; Cepstrum; Databases; Electronic mail; Frequency; Hidden Markov models; Informatics; Mutual information; Natural languages; Speech analysis; TV broadcasting;
Conference_Titel :
TENCON 99. Proceedings of the IEEE Region 10 Conference
Conference_Location :
Cheju Island
Print_ISBN :
0-7803-5739-6
DOI :
10.1109/TENCON.1999.818357
