Research Of Speaker Recognition Based On Support Vector Data Description

Due to its special merits of flexibility, accuracy and economy, speaker recognition technology has been regarded as the most natural kind of biometrics, which has comprehensive perspective of applications in the field of security access, forensics evaluation, electronic sniff, financial services. Recently the speaker recognition system research has turned from theory to practice and people demands more and more with the change of circumstances. Seeking the higher recognition rate will never be the only criterion. The real-time quality can not be neglected as well as the convenience and expandability of the system model.In recent ten years, many classification algorithms were proposed based on the kernel function, which effectively solved the drawbacks of local minimum and incomplete statistical analysis of the traditional pattern recognition model. These new algorithms always have super power of nonlinear capacity which can meet the speech feature?s demanding. So speaker recognition systems based on density-induced support vector data description presented in this artical have been proved to be very successful.In this thesis, kernel classification method is proposed which can be applied to the task of speaker identification in the circumstance of small sample speech corpus. The main contributions of the work are as follows:(1) The parameters LPCC and MFCC including their extraction process and method are described in detail which are the most widely used in speaker recognition.(2) Introduced the basic theory of SVM, classical SVM supports only the case of binary classification, we expanded its multivariate by"one vs one"or"one vs rest"and used in speaker recognition(3) When applied in Speaker Recognition, SVDD needs only one class samples for every speaker in every model, which means the multi-class recognition can be naturally implemented. Proposed the density-induced support vector data domain description method. The purpose of data description is to give a compact description of the target data that represents most of its characteristics. In a support vector data description (SVDD), the compact description of target data is given in a hyperspherical model, which is determined by a small portion of data called support vectors. Despite the usefulness of the conventional SVDD, however, it may not identify the optimal solution of target description especially when the support vectors do not have the overall characteristics of the target data. To address the issue in SVDD methodology, the DISVDD is proposed introducing new distance measurements based on the notion of a relative density degree for each data point in order to reflect the distribution of a given data set. Experiments are made for comparison between GMM and the proposed DISVDD because they both can apply for open-set speaker identification, the results show that the DISVDD outperforms the GMM whenever in recognition rate, real-time ability and sample demanding.(4) More and more occasions for the use of biometric technologies to improve the security of information, the voiceprint lock?s accuracy rate and instantaneity can be enhanced to some extent with the algorithm of DISVDD.(5) Finally, a summary is made and some future works about voiceprint identification system are presented.