Classification in the Speech Recognition

This paper presents specific approach of the classification of the incorrect speech sounds. Sampled data are vowels gathered during the speech therapy with children that have difficulties to pronounce them correctly. Continuous wavelet transformation has been applied on these incorrectly pronounce vowels using Morlet wavelet. Coefficients have been analyzed in the context of three main formants that characterized each of the vowels. The selected coefficients have been classified into main clusters, and have been compared with the one obtained for correct signals. At the end some improvements have been proposed in order to use results in the daily speech therapy and to automate process. Data that is used in analysis is gathered during the speech therapy with the children of age between 12 and 14 years. Session is supervised by speech therapist that listens and guides patient to pronounce vowels correctly. The process is very time consuming and will benefit from some elements of automation and provision of feedback to patients by the expert system. Sound features of language can be viewed in several ways. The first way is that the signals are grouped in terms of distribution of acoustic energy in the resonant field, which is caused by speech, which is the acoustic side of the problem, and this approach is given in this paper. Another way is to look at the voice signals from the point of hearing and the ability to receive those signals and to implement parts of the brain, in

[1]  J.-H. Zhou,et al.  Reinforced Morlet wavelet transform for bearing fault diagnosis , 2010, IECON 2010 - 36th Annual Conference on IEEE Industrial Electronics Society.

[2]  Patrick A. Naylor,et al.  Voice source parameters for speaker verification , 1998, 9th European Signal Processing Conference (EUSIPCO 1998).

[3]  Bayya Yegnanarayana,et al.  Epoch Extraction From Speech Signals , 2008, IEEE Transactions on Audio, Speech, and Language Processing.

[4]  Ingrid Daubechies.  Recent results in wavelet applications , 1998, J. Electronic Imaging.

[5]  Nor Ashidi Mat Isa,et al.  Denoising-based clustering algorithms for segmentation of low level salt-and-pepper noise-corrupted images , 2010, IEEE Transactions on Consumer Electronics.

[6]  Jr. L.R. Litwin.  Speech coding with wavelets , 1998 .

[7]  S. Hariprasath,et al.  Biometric personal identification based on iris pattern recognition using Wavelet Packet Transform , 2010, 2010 Second International conference on Computing, Communication and Networking Technologies.

[8]  Chia-Hung Lin,et al.  Adaptive wavelet networks for power-quality detection and discrimination in a power system , 2006 .

[9]  Lu Bibo,et al.  Iris Recognition Method Based on the Coefficients of Morlet Wavelet Transform , 2010, 2010 International Conference on Intelligent Computation Technology and Automation.

[10]  Deepak S. Turaga,et al.  On K-Means Cluster Preservation Using Quantization Schemes , 2009, 2009 Ninth IEEE International Conference on Data Mining.

[11]  Jianhua Lu,et al.  A symbol rate estimation algorithm based on Morlet wavelet transform and autocorrelation , 2009, 2009 IEEE Youth Conference on Information, Computing and Telecommunication.

[12]  Hui Li.  Complex Morlet wavelet amplitude and phase map based bearing fault diagnosis , 2010, 2010 8th World Congress on Intelligent Control and Automation.

[13]  Khaled Daqrouq,et al.  The use of wavelets in speaker feature tracking identification system using neural network , 2009 .

[14]  Claire Cardie,et al.  Clustering with Instance-Level Constraints , 2000, AAAI/IAAI.

[15]  Jalal Karam,et al.  A comprehensive approach for speech related multimedia applications , 2010 .

[16]  Mirjam Sepesy Maučec,et al.  Slovenian spontaneous speech recognition and acoustic modeling of filled pauses and onomatopoeas , 2008 .

[17]  Umi Kalthum Ngah,et al.  Adaptive fuzzy moving K-means clustering algorithm for image segmentation , 2009, IEEE Transactions on Consumer Electronics.

[18]  He Li,et al.  K-Means on Commodity GPUs with CUDA , 2009, 2009 WRI World Congress on Computer Science and Information Engineering.

[19]  N.C.F. Tse.  Practical application of wavelet to power quality analysis , 2006, 2006 IEEE Power Engineering Society General Meeting.

[20]  Biing-Hwang Juang,et al.  The past, present, and future of speech processing , 1998, IEEE Signal Process. Mag..

[21]  Bai Sen,et al.  Robust Information Hiding in Speech Signal Based on Pitch Period Prediction , 2010, 2010 International Conference on Computational and Information Sciences.