A new feature extraction front-end for robust speech recognition using progressive histogram equalization and multi-eigenvector temporal filtering.
Shang-nien TsaiLin-Shan LeePublished in: INTERSPEECH (2004)
Keyphrases
- histogram equalization
- feature extraction
- temporal filtering
- image enhancement
- contrast enhancement
- gray scale
- image contrast
- spatial filtering
- image processing
- wavelet transform
- gray level
- motion estimation
- multiresolution
- gabor filters
- speech signal
- image analysis
- feature space
- multiscale
- face recognition
- feature selection