Robust speech recognition features based on temporal trajectory filtering of frequency band spectrum.
Jia-Lin ShenWen-Liang HwangLin-Shan LeePublished in: ICSLP (1996)
Keyphrases
- speech recognition
- spectral subtraction
- frequency band
- speech recognition systems
- noisy environments
- pattern recognition
- speech recognizer
- hidden markov models
- cepstral coefficients
- frequency spectrum
- speaker identification
- speech recognition technology
- language model
- speech synthesis
- speech signal
- speaker independent
- automatic speech recognition
- high frequency
- feature vectors
- spectrum sensing
- feature extraction
- image processing
- low frequency
- multi band
- bandpass
- noise reduction
- n gram
- image quality
- feature set
- feature space
- face recognition