한국어 격리단어 인식 시스템에서 HMM 파라미터의 화자 적응

Speaker Adaptation in HMM-based Korean Isoklated Word Recognition

  • 오광철 (KAIST 전기 및 전자공학과) ;
  • 이황수 (KAIST 전기 및 전자공학과) ;
  • 은종관 (KAIST 전기 및 전자공학과)
  • 발행 : 1991.04.01

초록

This paper describes performances of speaker adaptation using a probabilistic spectral mapping matrix in hidden-Markov model(HMM) -based Korean isolated word recognition. Speaker adaptation based on probabilistic spectral mapping uses a well-trained prototype HMM's and is carried out by Viterbi, dynamic time warping, and forward-backward algorithms. Among these algorithms, the best performance is obtained by using the Viterbi approach together with codebook adaptation whose improvement for isolated word recognition accuracy is 42.6-68.8 %. Also, the selection of the initial values of the matrix and the normalization in computing the matrix affects the recognition accuracy.

키워드