Synthesized stereo mapping via deep neural networks for noisy speech recognition.
Jun DuLi-Rong DaiQiang HuoPublished in: ICASSP (2014)
Keyphrases
- feature space
- speech recognition
- neural network
- noisy environments
- pattern recognition
- hidden markov models
- language model
- automatic speech recognition
- speech signal
- speech synthesis
- speaker identification
- speech understanding
- speech recognizer
- speech recognition systems
- computer vision
- speech processing
- speech recognition technology
- handwriting recognition
- keyword spotting
- principal component analysis
- speech recognizers
- background noise
- multilayer perceptron
- speaker independent
- word recognition
- speech enhancement
- speaker dependent