A GMM-Based Robust Incremental Adaptation with a Forgetting Factor for Speaker Verification

  • Eunyoung Kim
  • Minkyung Kim
  • Younghwan Lim
  • Changwoo Seo
Conference paper

DOI: 10.1007/978-3-642-14932-0_24

Part of the Lecture Notes in Computer Science book series (LNCS, volume 6216)
Cite this paper as:
Kim E., Kim M., Lim Y., Seo C. (2010) A GMM-Based Robust Incremental Adaptation with a Forgetting Factor for Speaker Verification. In: Huang DS., Zhang X., Reyes García C.A., Zhang L. (eds) Advanced Intelligent Computing Theories and Applications. With Aspects of Artificial Intelligence. Lecture Notes in Computer Science, vol 6216. Springer, Berlin, Heidelberg

Abstract

Speaker recognition (SR) system uses a speaker model-adaptation method with testing sets to obtain a high performance. However, in the conventional adaptation method, when new data contain outliers, such as a noise or a change in utterance, an inaccurate speaker model results. As time elapses, the rate at which new data are adapted is reduced. The proposed method uses robust incremental adaptation (RIA) to reduce the effects of outliers and uses a forgetting factor to maintain the adaptive rate of new data in a Gaussian mixture model (GMM). Experimental results from a data set gathered over seven months show that the proposed algorithm is robust against outliers and maintains the adaptive rate of new data.

Keywords

Speaker verification (SV) Gaussian mixture model (GMM) incremental adaptation forgetting factor 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Eunyoung Kim
    • 1
  • Minkyung Kim
    • 1
  • Younghwan Lim
    • 1
  • Changwoo Seo
    • 2
  1. 1.Department of MediaSoongsil UniversitySeoulKorea
  2. 2.Medical & IT Fusion Research DivisionKorea Electrotechnology Research InstituteAnsan-cityKorea

Personalised recommendations