Deep Neural Network-based Speech Separation Combining with MVDR Beamformer for Automatic Speech Recognition System.
Bong-Ki LeeJaewoong JeongPublished in: ICCE (2019)
Keyphrases
- minimum variance
- neural network
- speech recognition
- data driven
- linear prediction
- recognition engine
- speech music discrimination
- genetic algorithm
- multi modal
- fully automatic
- speech signal
- multipath
- hearing impaired
- speech transcripts
- speech synthesis
- speaker identification
- audio visual
- semi automatic
- question answering
- pattern recognition
- machine learning