Multi speaker text-to-speech synthesis using generalized end-to-end loss function.
Owais NazirAruna MalikSamayveer SinghAl-Sakib Khan PathanPublished in: Multim. Tools Appl. (2024)
Keyphrases
- end to end
- loss function
- text to speech synthesis
- pairwise
- support vector
- ad hoc networks
- bayes rule
- admission control
- boosting framework
- congestion control
- wireless ad hoc networks
- empirical risk
- risk minimization
- rate allocation
- stochastic gradient descent
- transport layer
- application layer
- internet protocol
- learning to rank
- convex loss functions
- real time
- scalable video
- high bandwidth
- precision and recall
- machine learning