Fusion Feature Extraction Based on Auditory and Energy for Noise-Robust Speech Recognition.
Yanyan ShiJing BaiPeiyun XueDianxi ShiPublished in: IEEE Access (2019)
Keyphrases
- speech recognizers
- speech recognition
- noisy environments
- speech recognizer
- feature extraction
- automatic speech recognition
- speaker identification
- pattern recognition
- speech signal
- cepstral coefficients
- language model
- speech synthesis
- speech processing
- background noise
- hidden markov models
- speaker verification
- noisy speech
- signal processing
- speech recognition technology
- speech enhancement
- digit recognition
- signal to noise ratio
- speech recognition errors
- image classification
- visual speech
- speaker independent
- isolated word
- noise reduction
- natural language processing
- wavelet transform
- face recognition
- image processing
- machine learning
- speaker recognition
- principal component analysis
- feature selection
- neural network