Efficient online target speech extraction using DOA-constrained independent component analysis of stereo data for robust speech recognition.
Minook KimHyung-Min ParkPublished in: Signal Process. (2015)
Keyphrases
- speech recognition
- independent component analysis
- speech synthesis
- principal component analysis
- speech signal
- hidden markov models
- automatic speech recognition
- pattern recognition
- language model
- independent components
- speech processing
- training data
- speaker dependent
- data mining
- word error rate
- maximum likelihood
- signal processing
- computer vision