Non-Parallel Whisper-to-Normal Speaking Style Conversion Using Auxiliary Classifier Variational Autoencoder.
Shogo SekiHirokazu KameokaTakuhiro KanekoKou TanakaPublished in: IEEE Access (2023)
Keyphrases
- face detection
- object detection
- face recognition
- support vector
- image segmentation
- training data
- feature space
- classifier systems
- classification process
- feature selection
- decision trees
- classification scheme
- classification algorithm
- conversational agents
- learning algorithm
- linear classifiers
- parallel processing
- class labels
- feature set
- support vector machine
- ensemble learning
- svm classifier
- classification rate
- shared memory
- learning classifier systems
- ensemble classifier
- learning phase
- distributed memory
- optical flow