Neural MOS Prediction for Synthesized Speech Using Multi-Task Learning with Spoofing Detection and Spoofing Type Classification.
Yeunju ChoiYoungmoon JungHoirin KimPublished in: SLT (2021)
Keyphrases
- multi task learning
- multi task
- multiple tasks
- feature extraction
- learning tasks
- neural network
- decision trees
- gaussian processes
- learning problems
- classification accuracy
- machine learning
- multi label image annotation
- binary classification tasks
- classification models
- image classification
- unsupervised learning
- theoretical analysis
- transfer learning
- high order
- multi class
- multitask learning
- support vector
- feature selection
- machine learning algorithms
- text classification
- supervised learning
- support vector machine
- knn
- feature space
- synthesized speech