Multi-layered Features with SVM for Text-independent Speaker Verification

Yin-Guo Li, Qin Wei, Thomas Fang Zheng, Yang-Rui Yang
2012 2012 International Conference on Computer Science and Service System  
In this paper, we propose an approach for textindependent speaker verification system usage both cepstral and prosodic features. We combine MFCC features and pitch contour features to capture the characteristics in speaker verification. We are using cubic polynomials to estimate the pitch contour segments in order to model the differences on intonation contour, and using the support vector machine (SVM) to measure overall system's effectiveness. Experimental results show that the proposed
more » ... the proposed approach can significantly improve the text-independent speaker recognition.
doi:10.1109/csss.2012.101 fatcat:rvisim3ymbgbvobjlho7ydevgq