On the Discrimination of Speech/Music Using a Time Series Regularity

A new method to discriminate between speech and music related to the automatic transcription of broadcast news is presented. In the proposed method, a time series regularity, sample entropy (SampEn), is mainly used as an efficient feature to discriminate speech and music of broadcast audio stream. SampEn is a variant of the approximate entropy (ApEn) that measures the regularity of time series. Depending on the regularity of time series, a segment of a given audio stream is classified into speech or music. The first step of the method is calculation of SampEn sequence over windows. The second step is classification of this segment with a rule-based classification scheme over sample entropy sequence. Experimental results show the effectiveness of the proposed method for broadcast news shows with different music styles.