Speaker Identification in Small Training Data Environment using MLLR Adaptation Method

MLLR 화자적응 기법을 이용한 적은 학습자료 환경의 화자식별

  • Kim, Se-hyun (Voice Interface Lab. Div of Computer Science, Dept. of Electrical Engineering and Computer Science, KAIST) ;
  • Oh, Yung-Hwan (Voice Interface Lab. Div of Computer Science, Dept. of Electrical Engineering and Computer Science, KAIST)
  • 김세현 (한국과학기술원 전자전산학과 전산학전공 음성인터페이스연구실) ;
  • 오영환 (한국과학기술원 전자전산학과 전산학전공 음성인터페이스연구실)
  • Published : 2005.11.17

Abstract

Identification is the process automatically identify who is speaking on the basis of information obtained from speech waves. In training phase, each speaker models are trained using each speaker's speech data. GMMs (Gaussian Mixture Models), which have been successfully applied to speaker modeling in text-independent speaker identification, are not efficient in insufficient training data environment. This paper proposes speaker modeling method using MLLR (Maximum Likelihood Linear Regression) method which is used for speaker adaptation in speech recognition. We make SD-like model using MLLR adaptation method instead of speaker dependent model (SD). Proposed system outperforms the GMMs in small training data environment.

Keywords