DFT based feature extraction with non-uniform spectral compression for robust speech recognition.
Chun-Shing YipPublished in: ICASSP (2002)
Keyphrases
- speech recognition
- cepstral coefficients
- feature extraction
- noisy environments
- pattern recognition
- hidden markov models
- speaker identification
- frequency domain
- speech recognizer
- keyword spotting
- language model
- speech understanding
- automatic speech recognition
- speech synthesis
- speech signal
- speaker independent
- speech processing
- speaker adaptation
- speech recognition technology
- face recognition
- isolated word
- image processing
- feature space
- spectral analysis
- speech recognition systems
- image compression
- feature selection
- hyperspectral images
- compression ratio
- feature set
- speaker dependent
- speech recognizers
- audio visual speech recognition