BibTeX:

@article{IJIRSTV2I9003,
     title={Different Audio Feature Extraction using Segmentation },
     author={Gayatri M. Bhandari},
     journal={International Journal for Innovative Research in Science & Technology},
     volume={2},
     number={9},
     pages={1--5},
     year={},
     url={http://www.ijirst.org/articles/IJIRSTV2I9003.pdf},
     publisher={IJIRST (International Journal for Innovative Research in Science & Technology)},
}

Today's internet world consists of tremendous amount of audio and video data which is consuming more space on clouds and servers. Even streaming of such audio and video data requires lot of efforts from hardware as well as software point of view, which increase the cost of service. So today there is need to convert this audio/video into some digital form which can be easily accessible and the downloaded over the internet. Segmentation gives the best approach for dividing the multimedia data into digital data by extracting different features of multimedia data. This paper introduces new technique to segment the audio signals and extract the different features in feature vector so that this data will be reproduced after transmission over the internet. With feature extraction from audio, it is possible to recognize the content of a piece of audio. This paper explains the need for audio feature extraction system, and also describes the most important attributes such as Mel Frequency Cepstral Coefficient, Zero Crossing Ratio, Linear Predictive Coefficient, Signal to Noise Ratio, Spectrum Flux, Power Spectrum, RMS etc.

Audio segmentation, feature extraction, FFT, Magnitude Spectrum, Power Spectrum, ZCR, SNR, Constant, MFCC etc