On-line model compensation using noise masking effect for robust speech recognition

잡음 차폐를 이용한 온라인 모델 보상

  • 정규준 (한국과학기술원 전자전산학과 전산학전공) ;
  • 조훈영 (한국과학기술원 전자전산학과 전산학전공) ;
  • 오영환 (한국과학기술원 전자전산학과 전산학전공)
  • Published : 2003.05.01

Abstract

In this paper we apply PMC (parallel model combination) to speech recognition system online. As a representative of model based noise compensation techniques, PMC compensates environmental mismatch by combining pretrained clean speech models and real-time estimated noise information. This is very effective approach for compensating extreme environmental mismatch but is inadequate to use in on-line system for heavy computational cost. To reduce the computational cost and to apply PMC online, we use a noise masking effect - the energy in a frequency band is dominated either by clean speech energy or by noise energy - in the process of model compensation. Experiments on artificially produced noisy speech data confirm that the proposed technique is fast and effective for the on-line model compensation.

Keywords