Article ID Journal Published Year Pages File Type
385584 Expert Systems with Applications 2011 7 Pages PDF
Abstract

In this paper, the common vector approach (CVA) is newly used for text-independent speaker recognition. The performance of CVA is compared with those of Fisher’s linear discriminant analysis (FLDA) and Gaussian mixture models (GMM). The recognition rates obtained for the TIMIT database indicate that CVA and GMM are superior to FLDA. However, while the recognition rates obtained from CVA and GMM are identical, CVA enjoys advantages in terms of processing power and memory requirement. In order to obtain better results than those achieved with GMM, a new method which is a combination of CVA and GMM is proposed in this paper.

► The performance of CVA is compared with FLDA and GMM. ► A new method which is a combination of CVA and GMM is proposed for text-independent speaker recognition. ► The proposed CVA-based GMM is superior to GMM.

Related Topics
Physical Sciences and Engineering Computer Science Artificial Intelligence
Authors
, ,