Proceedings of the IEEK Conference (대한전자공학회:학술대회논문집)

The Institute of Electronics and Information Engineers (대한전자공학회)
권호 표지

Wavelet Filter Evaluation for Speech Recognition System

음성인식을 위한 웨이블릿 필터 평가

  • 김기대 (연세대학교 전기컴퓨터공학과) ;
  • 이철희 (연세대학교 전기컴퓨터공학과)
  • Published : 2000.06.01
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we explore the possibility to use wavelet decomposition based on modified octave structured 5-level filter banks as a set of features for speech recognition. The HMM (Hidden Markov Model) is used as a recognizer 〔l〕. We compared the performance of the wavelet decomposition with the mel-cepstrum and LPC cepstrum. Experimental results show favorable results.

Keywords