期刊名称：Oriental Journal of Computer Science and Technology
印刷版ISSN：0974-6471
出版年度：2017
卷号：10
期号：4
页码：736-744
语种：English
出版社：Oriental Scientific Publishing Company
摘要：The review and comparative analysis of the methods of compression and recognition of speech signals is carried out. The result of the carried out analysis of the existing recognition methods indicates, that all of them are based on the use of “inflexible” algorithms, which are badly adapted to the characteristic features of speech signals, thus degrading the efficiency of the operation of the whole recognition system. The necessity of the use of algorithms for determination of recognition features along with the use of the wavelet packet analysis as one of the advanced directions of the creation of the effective methods and principles of the development of the speech signals recognition systems is substantiated. Analysis of the compression methods with the use of the orthogonal transformations at the complete exception of minimal decomposition factors is conducted; a maximal possible compression degree is defined. In this compression method the orthogonal transformation of the signal segment with the subsequent exception of the set of the smallest modulo decomposition factors, irrespective of the order of their distribution, is conducted. Therefore the additional transfer of the information on the factors distribution is required. As a result, two information streams appear, the first one corresponds to the information stream on the decomposition factors, and the second stream transfers information on the distribution of these factors. Method of the determination of the speech signals recognition features and the algorithm for nonlinear time normalization is proposed and proved. Wavelet-packet transformation is adaptive, i.e. it allows adapting to the signal features more accurately by means of the choice of the proper tree of the optimal decomposition form, which provides the minimal number of wavelet factors at the prescribed accuracy of signal reconstruction, thus eliminating the information-surplus and unnecessary details of the signals. Estimation of the informativeness of the set of wavelet factors is accomplished by the entropy. In order to obtain the recognition factors, the spectral analysis operation is used. In order to carry out the temporary normalization, the deforming function is found, the use of which minimizes the discrepancy between the standard and new words realization. Dedicated to the determination of admissible compression factors on the basis of the orthogonal transformations use at the incomplete elimination of the set of minimal decomposition factors, to the creation of the block diagram of the method of the recognition features formation, to the practical testing of the software- methods. In order to elevate the compression factor, the adaptive uniform quantization is used, where the adaptation is conducted for all the decomposition factors. The program testing of the recognition methods is carried out by means of determination of the classification error probability using Mahalanobis (Gonzales) distance.
关键词：recognition of speech signals ; compression ; recognition features
