Nonparametric Speaker Recognition Method Using Earth Mover's Distance

• KUROIWA Shingo

  Faculty of Engineering, the University of Tokushima

• UMEDA Yoshiyuki

  Faculty of Engineering, the University of Tokushima

• TSUGE Satoru

  Faculty of Engineering, the University of Tokushima

• REN Fuji

  Faculty of Engineering, the University of Tokushima

Abstract

In this paper, we propose a distributed speaker recognition method using a nonparametric speaker model and Earth Mover's Distance (EMD). In distributed speaker recognition, the quantized feature vectors are sent to a server. The Gaussian mixture model (GMM), the traditional method used for speaker recognition, is trained using the maximum likelihood approach. However, it is difficult to fit continuous density functions to quantized data. To overcome this problem, the proposed method represents each speaker model with a speaker-dependent VQ code histogram designed by registered feature vectors and directly calculates the distance between the histograms of speaker models and testing quantized feature vectors. To measure the distance between each speaker model and testing data, we use EMD which can calculate the distance between histograms with different bins. We conducted text-independent speaker identification experiments using the proposed method. Compared to results using the traditional GMM, the proposed method yielded relative error reductions of 32% for quantized data.

Journal

• IEICE Trans. on Information and Systems, D

  IEICE Trans. on Information and Systems, D 89 (3), 1074-1081, 2006-03-01

  The Institute of Electronics, Information and Communication Engineers

Keywords

• distributed speaker recognition
• speaker identification
• nonparametric
• Earth Mover's Distance

Details

• CRID: 1572261551842025344
• NII Article ID: 110004719383
• NII Book ID: AA10826272
• ISSN: 09168532
• Text Lang: en
• Data Source:
  • CiNii Articles