End Point Detection for Wavelet Based Speech Compression

In real-field applications, the correct determination of voice segments highly improves the overall system accuracy and minimises the total computation time. This paper presents reliable measures of speech compression by detcting the end points of the speech signals prior to compressing them. The two different compession schemes used are the Global threshold and the Level- Dependent threshold techniques. The performance of the proposed method is tested wirh the Signal to Noise Ratios, Peak Signal to Noise Ratios and Normalized Root Mean Square Error parameter measures.

• Jalal Karam

• Wavelets
• End-points Detection
• Compression.

[1] Feng, Yanhui, Thanagasundram, Schlindwein, S., Soares, F., Discrete
wavelet-based thresholding study on acoustic emission signals to detect
bearing defect on a rotating machine, Thirteenth International Congress
on Sound and Vibration, Vienna, Austria July 2-6, 2006.
[2] Graps, A., An Introduction To Wavelets, IEEE Computational Sciences
and Engineering, Volume 2, Number 2, pp: 50-61, Summer 1995.
[3] Karam, J., and Karam, M., "Perfect Reconstruction of Hypermedia
Elements Via Filter Banks", International Journal of Computational and
Numerical Analysis and Applications, Vol 5 No. 1, 2004.
[4] Karam, J., A Global Threshold Wavelet-Based Scheme for Speech
Recognition, Third International conference on Computer Science, Software
Engineering Information Technology, E-Business and Applications,
Cairo, Egypt, Dec. 27-29 2004.
[5] Karam, J., Saad, R., The Effect of Different Compression Schemes on
Speech Signals, International Journal of Biomedical Sciences, Vol. 1 No.
4, pp: 230 234, 2006.
[6] Misiti, M., Misiti, Y., Oppenheim, G., Poggi, J., Matlab Wavelet Toolbox,
Math Works, Natick, MA, 1997.
[7] NIST, TIDIGITS, Speech Discs, Studio Quality Speaker-Independent
Connected-Digital Corpus, NTIS PB91-506592, Texas Instruments, Feb.
1991.
[8] NIST, Speech Discs 7-1.1, TI 46 Word Speech Database Speaker-
Dependent Isolated-Digital Corpus, LDC93S9, Texas Instruments, Sep.
1991.