Audio Content Analysis for Understanding Structures of Scene in Video

摘要

In this paper, we propose a system to categorize audio in 7 classes. For classification features, we use the mean and variance of RMS, ZCR, fundamental frequency and frequency peak which are extracted from every frame of 25ms length. In addition to the audio content classification, we also perform speaker identification with the voice sequences extracted automatically using our proposed method. The accuracy of our proposed scheme reaches 93.8% in categorizing audio signal and 80% in the speaker identification process.