Nature of Computation and Communication. International Conference, ICTCC 2014, Ho Chi Minh City, Vietnam, November 24-25, 2014, Revised Selected Papers

Research Article

Graph Based Semi-supervised Learning Methods Applied to Speech Recognition Problem

Download
270 downloads
  • @INPROCEEDINGS{10.1007/978-3-319-15392-6_26,
        author={Hoang Trang and Loc Tran},
        title={Graph Based Semi-supervised Learning Methods Applied to Speech Recognition Problem},
        proceedings={Nature of Computation and Communication. International Conference, ICTCC 2014, Ho Chi Minh City, Vietnam, November 24-25, 2014, Revised Selected Papers},
        proceedings_a={ICTCC},
        year={2015},
        month={2},
        keywords={Semi-supervised learning Graph laplacian Speech recognition MFCC},
        doi={10.1007/978-3-319-15392-6_26}
    }
    
  • Hoang Trang
    Loc Tran
    Year: 2015
    Graph Based Semi-supervised Learning Methods Applied to Speech Recognition Problem
    ICTCC
    ICST
    DOI: 10.1007/978-3-319-15392-6_26
Hoang Trang1,*, Loc Tran2,*
  • 1: Ho Chi Minh City University of Technology-VNU HCM
  • 2: University of Minnesota
*Contact email: hoangtrang@hcmut.edu.vn, tran0398@umn.edu

Abstract

Speech recognition is the important problem in pattern recognition research field. In this paper, the un-normalized, symmetric normalized, and random walk graph Laplacian based semi-supervised learning methods will be applied to the network derived from the MFCC feature vectors of the speech dataset. Experiment results show that the performance of the random walk and the symmetric normalized graph Laplacian based methods are at least as good as the performance of the un-normalized graph Laplacian based method. Moreover, the sensitivity measures of these three semi-supervised learning methods are much better than the sensitivity measure of the current state of the art Hidden Markov Model method in speech recognition problem.