Frequency-domain dereverberation on speech signal using surround retinex.
Mingming ZhangWeifeng LiLongbiao WangJianguo WeiZhiyong WuQingmin LiaoPublished in: APSIPA (2013)
Keyphrases
- frequency domain
- speech signal
- speech recognition
- spatial domain
- fourier transform
- image enhancement
- convolutive mixtures
- non stationary
- automatic speech recognition
- speaker identification
- hidden markov models
- noisy environments
- power spectrum
- adaptive filtering
- feature extraction
- subband
- denoising
- cross correlation
- spectral analysis
- filter bank
- speech quality
- contrast enhancement