Stereo-based stochastic mapping with discriminative training for noise robust speech recognition.
Xiaodong CuiMohamed AfifyYuqing GaoPublished in: ICASSP (2009)
Keyphrases
- speech recognition
- noisy environments
- discriminative training
- automatic speech recognition
- hidden markov models
- speech signal
- acoustic models
- speech synthesis
- speaker identification
- language model
- noisy speech
- speech recognizer
- background noise
- pattern recognition
- noise reduction
- speech enhancement
- maximum likelihood
- speech recognition technology
- speech recognition systems
- computer vision
- non stationary
- feature space
- speaker adaptation