Proceedings of the IEEK Conference (대한전자공학회:학술대회논문집)
- 2000.06d
- /
- Pages.127-130
- /
- 2000
Wavelet Filter Evaluation for Speech Recognition System
음성인식을 위한 웨이블릿 필터 평가
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