Feature extraction based on zero-crossings with peak amplitudes for robust speech recognition in noisy environments.
Doh-Suk KimJae-Hoon JeongJae-Weon KimSoo-Young LeePublished in: ICASSP (1996)
Keyphrases
- noisy environments
- speech recognition
- feature extraction
- speaker identification
- speech signal
- zero crossing
- speaker verification
- automatic speech recognition
- pattern recognition
- digit recognition
- language model
- cepstral coefficients
- hidden markov models
- noise reduction
- background noise
- speech synthesis
- scale space
- speech enhancement
- wavelet transform
- mel frequency cepstral coefficients
- feature vectors
- speaker recognition
- noisy speech
- voice activity detection
- palmprint
- edge detection
- co occurrence
- probabilistic model
- multiscale