Nonlinear Compensation Using the Gauss-Newton Method for Noise-Robust Speech Recognition.
Yong ZhaoBiing-Hwang JuangPublished in: IEEE Trans. Speech Audio Process. (2012)
Keyphrases
- speech recognition
- noisy environments
- newton method
- hidden markov models
- speech signal
- language model
- automatic speech recognition
- background noise
- pattern recognition
- speech recognition systems
- convergence analysis
- speech enhancement
- linear equations
- global convergence
- noise level
- optimality conditions
- computer vision
- neural network