GENRE CLASSIFICATION-SYSTEM OF TV SOUND SIGNALS BASED ON A SPECTROGRAM ANALYSIS

In this paper, a genre classification system of TV sound signals is pr oposed to provide a proper timbre automatically to the listener. The s pectral and temporal properties of TV sound are analyzed using the spe ctrogram principle to classify the genre. Some acoustic features such as the frequency distribution energy variation, etc. are extracted for classification. The sound is first classified into speech or music si gnals and the music signals are again divided into popular, jazz, or c lassical mode. After the classification, the frequency gain of the sou nd is regulated by the existing compensation data according to the gen re. The proposed system is implemented using 7 bandpass filters, an 8- bit microprocessor, and a threshold circuit for calculating the silenc e interval of the signal. From the experimental results, the classific ation accuracy of speech and music was 95%, and the accuracy between p opular, jazz, and classical music was 75%, 30%, and 60%, respectively.