Deep recurrent de-noising auto-encoder and blind de-reverberation for reverberated speech recognition.
Felix WeningerShinji WatanabeYuuki TachiokaBjörn W. SchullerPublished in: ICASSP (2014)
Keyphrases
- speech recognition
- denoising
- hidden markov models
- language model
- image denoising
- speech signal
- automatic speech recognition
- speech synthesis
- speech processing
- pattern recognition
- bit rate
- noisy environments
- speech recognition technology
- speaker identification
- wavelet domain
- noisy images
- speech recognizer
- speech recognition systems
- keyword spotting
- image processing
- speaker independent
- speech recognition errors
- speech recognizers
- speaker dependent