Using Support Vector Machines and two dimensional discrete cosine transform in speech automatic recognition.
Gracieth Cavalcanti BatistaWashington Luis Santos SilvaPublished in: IJCNN (2015)
Keyphrases
- automatic recognition
- discrete cosine transform
- image compression
- transform domain
- dct coefficients
- filter bank
- speech recognition
- three dimensional
- jpeg images
- speech signal
- dct domain
- compressed images
- blocking artifacts
- coded images
- subband
- lapped transforms
- fast fourier transform
- image coding
- image blocks
- spatial domain
- post processing
- wavelet transform
- multiscale
- feature selection