Title :
Speech enhancement based on spectral subtraction for speech recognition system
Author :
Han, Jung-woo ; Kim, Se-young ; Kim, Ki-Man ; Jung, Ji-Won ; Yun, Young
Author_Institution :
Dept. of Radio Commun. Eng., Korea Maritime Univ., Busan, South Korea
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.
Keywords :
acoustic distortion; acoustic signal processing; reverberation; spectral analysis; speech enhancement; speech recognition; acoustical distortion; automatic speech recognition system; reverberation; spectral entropy; spectral subtraction; speech enhancement; speech signal; voice activity detection; Algorithm design and analysis; Entropy; Reverberation; Signal processing algorithms; Speech; Speech enhancement; Speech recognition;
Conference_Titel :
Consumer Electronics (ICCE), 2011 IEEE International Conference on
Conference_Location :
Las Vegas, NV
Print_ISBN :
978-1-4244-8711-0
DOI :
10.1109/ICCE.2011.5722659
