A neural predictive coding feature extraction scheme in DCT domain for phoneme recognition.
Mahmood Yousefi-AzarFarbod RazzaziPublished in: Neural Comput. Appl. (2012)
Keyphrases
- dct domain
- predictive coding
- transform domain
- spatial domain
- post processing
- dct coefficients
- motion compensated
- lossless compression
- video coding
- human visual system
- entropy coding
- compressed domain
- digital video
- discrete cosine transform
- compressed images
- low frequency
- reference frame
- distributed video coding
- bit rate
- image blocks
- macroblock
- motion compensation
- non stationary
- image compression
- motion estimation
- compression ratio
- motion vectors
- similarity measure
- frequency domain
- image quality
- pattern recognition