Convolutional Variational Autoencoders for Audio Feature Representation in Speech Recognition Systems.
Olga YakovenkoIvan BondarenkoPublished in: TPNC (2020)
Keyphrases
- feature representation
- speech recognition systems
- speech recognition
- mel frequency cepstral coefficients
- speaker identification
- feature set
- speech recognizer
- feature extraction
- broadcast news
- denoising
- face recognition
- low dimensional
- image segmentation
- sparse representation
- signal processing
- audio features
- hidden markov models
- audio visual
- pattern recognition
- deep learning
- visual information
- classification accuracy
- high dimensional
- spectral features
- automatic speech recognition
- visual data
- neural network
- language model
- image processing
- acoustic features
- speaker recognition
- texture features
- bayesian networks