Continuous speech recognition in noise using spectral subtraction and HMM adaptation.
Juan Arturo Nolazco-FloresSteve J. YoungPublished in: ICASSP (1) (1994)
Keyphrases
- spectral subtraction
- continuous speech recognition
- speech recognition
- speech signal
- hidden markov models
- speaker adaptation
- automatic speech recognition
- noisy speech
- background noise
- noisy environments
- non stationary
- speech enhancement
- language model
- signal to noise ratio
- linear prediction
- hearing aids
- noise model
- additive noise
- speech synthesis
- noise reduction
- pattern recognition
- neural network
- noise removal
- noisy images
- image coding
- multiscale
- feature extraction
- feature selection
- information retrieval