Proceedings of the IEEK Conference (대한전자공학회:학술대회논문집)

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

CASA-based Front-end Using Two-channel Speech for the Performance Improvement of Speech Recognition in Noisy Environments

잡음환경에서의 음성인식 성능 향상을 위한 이중채널 음성의 CASA 기반 전처리 방법

  • Park, Ji-Hun (Department of Information and Communication Gwangju Institute of Science and Technology) ;
  • Yoon, Jae-Sam (Department of Information and Communication Gwangju Institute of Science and Technology) ;
  • Kim, Hong-Kook (Department of Information and Communication Gwangju Institute of Science and Technology)
  • 박지훈 (광주과학기술원 정보통신공학과) ;
  • 윤재삼 (광주과학기술원 정보통신공학과) ;
  • 김홍국 (광주과학기술원 정보통신공학과)
  • Published : 2007.07.11
Download PDF
⟨ Previous Next ⟩

Abstract

In order to improve the performance of a speech recognition system in the presence of noise, we propose a noise robust front-end using two-channel speech signals by separating speech from noise based on the computational auditory scene analysis (CASA). The main cues for the separation are interaural time difference (ITD) and interaural level difference (ILD) between two-channel signal. As a result, we can extract 39 cepstral coefficients are extracted from separated speech components. It is shown from speech recognition experiments that proposed front-end has outperforms the ETSI front-end with single-channel speech.

Keywords