Feature analysis and extraction for audio automatic classification

Feature analysis and extraction are the foundation of audio automatic classification. This paper divides audio streams into five classes: silence, noise, pure speech, speech over background sound and music. We present our work on audio feature analysis and extraction on the frame level and clip level. Four new features are proposed, including silence ratio, pitch frequency standard deviation, harmonicity ratio and smooth pitch ratio. We have presented an SVM based approach to classification. The effectiveness of the features is evaluated in experiments. Experiment results show that the features we selected and proposed are rational and effective.