Statistical Beamformer Exploiting Non-stationarity and Sparsity with Spatially Constrained ICA for Robust Speech Recognition.
Ui-Hyeop ShinHyung-Min ParkPublished in: CoRR (2023)
Keyphrases
- speech recognition
- noisy environments
- hidden markov models
- automatic speech recognition
- language model
- speech processing
- speech synthesis
- speech recognition systems
- pattern recognition
- independent component analysis
- speech signal
- speech recognizer
- speech understanding
- speaker identification
- speech recognition technology
- signal to noise ratio
- non stationary
- speech recognition errors
- audio visual speech recognition
- isolated word
- speaker independent
- feature extraction
- speaker recognition
- neural network