Robust speech recognition with spectral subtraction in low SNR.
Randy GomezAkinobu LeeHiroshi SaruwatariKiyohiro ShikanoPublished in: INTERSPEECH (2004)
Keyphrases
- speech recognition
- spectral subtraction
- low snr
- speech signal
- noisy environments
- hidden markov models
- noisy speech
- noise model
- signal to noise ratio
- language model
- automatic speech recognition
- speech synthesis
- pattern recognition
- speech recognition systems
- speaker verification
- feature extraction
- image segmentation
- machine learning
- subband
- wavelet transform
- multiscale
- speaker identification