← Back to VOLUME 2, ISSUE 8, AUGUST 2013
This work is licensed under a Creative Commons Attribution 4.0 International License.
Study of Audio-Visual Feature in Noisy Background
PRIYANKA SHARMA, PARUL DIHULIA, VIKAS GUPTA Research Scholar, EC Department, TIT, Bhopal, Madhya Pradesh, India Assistant Professor, EC Department, TIT, Bhopal, Madhya Pradesh, India Head of Department, EC Department, TIT, Bhopal, Madhya Pradesh, India
Downloads: Download PDF
π 43 viewsπ₯ 1 download
Abstract: In recent development of technology the world is been surrounded by the latest technology which are based on man machine interaction. The key role is played by mobile phone and video conferencing in which quality of speech is the main criteria. Here in this paper we have reported the enhancement of Audio Speech recognition with the help of visual feature in noisy background. For extracting visual feature DCT along with the Wavelet is used and audio feature are extracted using MFCC feature. Further the results are reported at different signal to noise ratio (SNR) i.e. ranging between 20 dB to -5 dB using AWGN.
Keywords: DCT, MFCC, SNR, Speech
Keywords: DCT, MFCC, SNR, Speech
How to Cite:
[1] PRIYANKA SHARMA, PARUL DIHULIA, VIKAS GUPTA Research Scholar, EC Department, TIT, Bhopal, Madhya Pradesh, India Assistant Professor, EC Department, TIT, Bhopal, Madhya Pradesh, India Head of Department, EC Department, TIT, Bhopal, Madhya Pradesh, India, βStudy of Audio-Visual Feature in Noisy Background,β International Journal of Advanced Research in Computer and Communication Engineering (IJARCCE)
This work is licensed under a Creative Commons Attribution 4.0 International License.