Noise adaptive stream fusion based on feature component rejection for robust multi-stream speech recognition.
Jun ZhangYizhi FengGengxin NingFei JiPublished in: ICACI (2015)
Keyphrases
- multi stream
- audio visual speech recognition
- speech recognition
- hidden markov models
- noisy environments
- audio visual
- speech signal
- noisy speech
- speech recognizer
- speech synthesis
- automatic speech recognition
- noise reduction
- cepstral coefficients
- background noise
- speaker identification
- language model
- speaker independent
- image features
- emotion recognition
- speaker verification
- signal to noise ratio
- bayesian networks
- pattern recognition
- neural network
- feature vectors
- speech enhancement
- noise model
- image sequences
- machine learning