Reverberant speech recognition combining deep neural networks and deep autoencoders augmented with a phone-class feature.
Masato MimuraShinsuke SakaiTatsuya KawaharaPublished in: EURASIP J. Adv. Signal Process. (2015)
Keyphrases
- speech recognition
- speech signal
- neural network
- pattern recognition
- hidden markov models
- speech processing
- automatic speech recognition
- language model
- cepstral coefficients
- speech synthesis
- noisy environments
- speech recognition technology
- acoustic models
- computer vision
- keyword spotting
- natural language
- deep learning
- speech recognizer
- speaker independent
- speaker identification
- speech recognition errors
- speaker dependent
- speech recognizers
- background noise
- speech recognition systems
- speech enhancement
- speaker diarization
- back propagation
- denoising
- feature space
- data mining