Smoothed spectral subtraction for a frequency-weighted HMM in noisy speech recognition.
Hiroshi MatsumotoNoboru NaitohPublished in: ICSLP (1996)
Keyphrases
- speech recognition
- spectral subtraction
- noisy environments
- speech signal
- hidden markov models
- noisy speech
- hybrid method
- cepstral coefficients
- language model
- automatic speech recognition
- speech recognizer
- speech synthesis
- speaker identification
- speaker independent
- keyword spotting
- speech enhancement
- pattern recognition
- background noise
- handwriting recognition
- speaker verification
- speech recognition systems
- low frequency
- vocal tract
- linear prediction
- multi channel
- image processing