No abstract

No abstract

No abstract

Reverberation is acoustical distortion which degrades the fidelity and intelligibility of speech signal in a speech recognition system. This paper presents a speech enhancement algorithm using an one-microphone for automatic speech recognition system. The proposed algorithm is based on a simple spectral subtraction. To further improve system performance, we employ a method of Voice Activity Detection (VAD) using spectral entropy.

This paper proposes a dereverberation system for speech enhancement using modified linear prediction (LP) residual in the reverberant room condition. We obtain a delayand-sum beamformer and new LP residual signal using modified LP residual combination, which derived from weighting of the LP residual and the Hilbert transform of LP residual.