Use of Generalised Nonlinearity in Vector Taylor Series Noise Compensation for Robust Speech Recognition.
Erfan LoweimiJon BarkerThomas HainPublished in: INTERSPEECH (2016)
Keyphrases
- speech recognition
- noisy environments
- taylor series
- speech signal
- language model
- hidden markov models
- automatic speech recognition
- pattern recognition
- background noise
- speaker identification
- noise reduction
- speech synthesis
- noisy speech
- speech recognition technology
- speech enhancement
- speech recognizer
- feature vectors
- noise level
- speech recognition systems
- speaker dependent
- color filter array
- numerical integration
- image quality
- neural network