A novel silent speech recognition approach based on parallel inception convolutional neural network and Mel frequency spectral coefficient.
Jinghan WuYakun ZhangLiang XieYe YanXu ZhangShuang LiuXingwei AnErwei YinDong MingPublished in: Frontiers Neurorobotics (2022)
Keyphrases
- cepstral coefficients
- speech recognition
- convolutional neural network
- speech signal
- language model
- face detection
- hidden markov models
- pattern recognition
- automatic speech recognition
- speech synthesis
- linear prediction
- speech processing
- speech recognition technology
- speech understanding
- speech recognizer
- speaker identification
- noisy environments
- speaker independent
- speech recognition systems
- speech recognizers
- lossless compression
- feature set
- object recognition
- feature extraction
- neural network