Selective Speech Feature Extraction using Channel Similarity in CHMM Vocabulary Recognition

CHMM 어휘인식에서 채널 유사성을 이용한 선택적 음성 특징 추출

  • Oh, Sang Yeon (Dept. of Computer Media Convergence, Gachon University)
  • 오상엽 (가천대학교 컴퓨터미디어융합학과)
  • Received : 2013.08.12
  • Accepted : 2013.10.20
  • Published : 2013.10.28


HMM Speech recognition systems have a few weaknesses, including failure to recognize speech due to the mixing of environment noise other voices. In this paper, we propose a speech feature extraction methode using CHMM for extracting selected target voice from mixture of voices and noises. we make use of channel similarity and correlate relation for the selective speech extraction composes. This proposed method was validated by showing that the average distortion of separation of the technique decreased by 0.430 dB. It was shown that the performance of the selective feature extraction is better than another system.


Speech recognition;correlation;voice extract;channel similarity


Supported by : 가천대학교

Cited by

  1. Bayesian Method Recognition Rates Improvement using HMM Vocabulary Recognition Model Optimization vol.12, pp.7, 2014,