SNR-dependent non-uniform spectral compression for noisy speech recognition.
Kam-keung ChuShu Hung LeungPublished in: ICASSP (1) (2004)
Keyphrases
- speech recognition
- noisy environments
- speech enhancement
- signal to noise ratio
- speaker adaptation
- cepstral coefficients
- speech signal
- noise reduction
- hidden markov models
- automatic speech recognition
- pattern recognition
- compression algorithm
- image compression
- language model
- speech processing
- speech synthesis
- linear prediction
- handwriting recognition
- speaker identification
- speech recognition systems
- speech recognizer
- background noise
- spectral analysis
- compression ratio
- speech retrieval
- isolated word
- neural network
- hyperspectral
- digit recognition
- speech recognition technology
- remote sensing
- keyword spotting
- speaker independent
- non stationary
- signal processing
- edge detection
- speech recognizers