Analysis of Speaker Verification System Using Support Vector Machine

2017 ◽  
Vol 13 (10) ◽  
pp. 6531-6542
Author(s):  
P Shanmugapriya ◽  
Y. Venkataramani
Keyword(s):  
Support Vector Machine ◽  
Speaker Recognition ◽  
Speaker Verification ◽  
Fuzzy Theory ◽  
Support Vector ◽  
Fuzzy Support Vector Machine ◽  
System A ◽  
Verification System ◽  
Svm Model

The integration of GMM- super vector and Support Vector Machine (SVM) has become one of most popular strategy in text-independent speaker verification system.  This paper describes the application of Fuzzy Support Vector Machine (FSVM) for classification of speakers using GMM-super vectors. Super vectors are formed by stacking the mean vectors of adapted GMMs from UBM using maximum a posteriori (MAP). GMM super vectors characterize speaker’s acoustic characteristics which are used for developing a speaker dependent fuzzy SVM model. Introducing fuzzy theory in support vector machine yields better classification accuracy and requires less number of support vectors. Experiments were conducted on 2001 NIST speaker recognition evaluation corpus. Performance of GMM-FSVM based speaker verification system is compared with the conventional GMM-UBM and GMM-SVM based systems.  Experimental results indicate that the fuzzy SVM based speaker verification system with GMM super vector achieves better performance to GMM-UBM system.  

Prediction of Classification of Rock Burst Risk Based on Genetic Algorithms with SVM

2014 ◽  
Vol 628 ◽  
pp. 383-389 ◽  
Author(s):  
Ya Hui Peng ◽  
Kang Peng ◽  
Jian Zhou ◽  
Zhi Xiang Liu
Keyword(s):  
Support Vector Machine ◽  
Genetic Algorithms ◽  
Rock Burst ◽  
Support Vector ◽  
Proposed Model ◽  
Svm Model ◽  
Rock Burst Risk ◽  
Rock Burst Prediction ◽  
Optimization Search

Due to the complex features of rock burst hazard assessment systems, a support vector machine (SVM) model for predicting of classification of rock burst was established based on the SVM theory and the actual characteristics of the project in this study. The main factors of rock burst, such as coal seam, dip, buried depth, structure situation, change of pitch angle, change of coal thickness, gas concentration, roof management, pressure relief and shooting were defined as the criterion indices for rock burst prediction in the proposed model. In order to determine reasonable and efficient the parameters of SVM, Firstly, the appropriate fitness function for genetic algorithms (GA) operation was determined, and then optimization parameters of SVM model were selected by real coded GA, therefore, the genetic algorithms and support vector machine (GSVM) model was established. A GSVM model was obtained through training 23 sets of measured data, the cross-validation method was introduced to verify the stability of GSVM model and the ratio of mis-discrimination is 0. Moreover, the proposed model was used to predict 12 new samples rock burst, the correct rate of prediction results is 91.6667% and are identical with actual situation. The results show that the genetic algorithm can speed up SVM parameter optimization search, the proposed model has a high credibility in the study of rock burst prediction of risk classification, which can be applied to practical engineering.

Vehicle Classification Algorithm Based on Fuzzy SVM Models

2013 ◽  
Vol 444-445 ◽  
pp. 841-848
Author(s):  
Yi Chen ◽  
Yu Hui Li ◽  
Fan Zhang ◽  
Feng Zhou
Keyword(s):  
Support Vector Machine ◽  
Classification Algorithm ◽  
Vehicle Classification ◽  
Support Vector ◽  
Binary Classifier ◽  
Sample Problem ◽  
Fuzzy Support Vector Machine ◽  
High Classification Accuracy ◽  
The Difference

As a typical binary classifier, its an inseparable sample problem about the Support Vector Machine (SVM) when processing the classification of the multi-class vehicle models. Since the SVM can not estimate the effect size of the samples classification accurately, and then reduces the classification generalization ability. In this paper, a fuzzy Support Vector Machine (FSVM) classification algorithm is applied to vehicle classification. According to the difference of the contribution which the vehicle characteristics make to the classification, the appropriate degree of membership is given, and the algorithm improves the vehicle models classification ability of the traditional SVM effectively. The experimental results show that the new method, compared with the existing vehicle classification method, is feasible, effective, and with a high classification accuracy

Sign in / Sign up

Export Citation Format

Share Document