• Title/Summary/Keyword: KMDA

Search Result 1, Processing Time 0.014 seconds

Improvement in Supervector Linear Kernel SVM for Speaker Identification Using Feature Enhancement and Training Length Adjustment (특징 강화 기법과 학습 데이터 길이 조절에 의한 Supervector Linear Kernel SVM 화자식별 개선)

  • So, Byung-Min;Kim, Kyung-Wha;Kim, Min-Seok;Yang, Il-Ho;Kim, Myung-Jae;Yu, Ha-Jin
    • The Journal of the Acoustical Society of Korea
    • /
    • v.30 no.6
    • /
    • pp.330-336
    • /
    • 2011
  • In this paper, we propose a new method to improve the performance of supervector linear kernel SVM (Support Vector Machine) for speaker identification. This method is based on splitting one training datum into several pieces of utterances. We use four different databases for evaluating performance and use PCA (Principal Component Analysis), GKPCA (Greedy Kernel PCA) and KMDA (Kernel Multimodal Discriminant Analysis) for feature enhancement. As a result, the proposed method shows improved performance for speaker identification using supervector linear kernel SVM.