Audio feature extraction plays an important role in analyzing and characterizing audio content. Auditory scene analysis, content-based retrieval, indexing, and fingerprinting of audio are few of the applications that require efficient feature extraction. The key to extract strong features that characterize the complex nature of audio signals is to identify their discriminatory subspaces. The audio information analysis for emotion recognition generally comprises linguistic and paralinguistic measurements. The linguistic measurement conforms to the rules of the language whereas paralinguistic measurement is the meta-data; i.e. related to how the words are spoken based on variations of pitch, intensity and spectral properties of the audio signal. This paper presents a technique for analyzing the features which extracted from recording audio signals in time domain and frequency domain by using statistical methods.
Al-Agha, S. A., Saleh, H. H., & Ghani, R. F. (2015). Analyze Features Extraction for Audio Signal with Six Emotions Expressions. International Journal of Engineering and Advanced Technology (IJEAT), (6), 2249–8958.