Title :
Environmental sound classification using spectral dynamic features
Author :
Karbasi, M. ; Ahadi, S.M. ; Bahmanian, M.
Author_Institution :
Electr. Eng. Dept., Amirkabir Univ. of Technol., Tehran, Iran
Abstract :
This paper presents a novel feature extraction method for environmental sounds classification. Although many kinds of audio features have been investigated for environmental sound classification tasks, most of them have been extracted only to model the speech signal structure, which explains their lower performance when dealing with other kinds of audio signals. The method proposed in this paper processes and extracts the spectral changes throughout the frames of a sound file and appends them to the frame-based spectral feature vectors as dynamic features. Experimental results show that proposed features outperform the commonly used audio features in context recognition tasks.
Keywords :
audio signal processing; feature extraction; signal classification; spectral analysis; speech recognition; audio feature extraction method; audio signals; context recognition task; dynamic feature; environmental sound classification; frame-based spectral feature vector; sound file; spectral change extraction; spectral dynamic feature; speech signal extraction; Feature extraction; Filter banks; Mel frequency cepstral coefficient; Noise measurement; Speech; Support vector machine classification; Vectors; audio classification; dynamic features; environmental sounds; feature extraction;
Conference_Titel :
Information, Communications and Signal Processing (ICICS) 2011 8th International Conference on
Conference_Location :
Singapore
Print_ISBN :
978-1-4577-0029-3
DOI :
10.1109/ICICS.2011.6173513