Generative Models for Improved Naturalness, Intelligibility, and Voicing of Whispered Speech.
Dominik WagnerSebastian P. BayerlHéctor A. Cordourier MaruriTobias BockletPublished in: CoRR (2022)
Keyphrases
- generative model
- endpoint detection
- speech recognition
- discriminative learning
- mixture model
- discriminative models
- conditional random fields
- probabilistic model
- em algorithm
- hierarchical hidden markov models
- semi supervised
- object categories
- maximum entropy principle
- prior knowledge
- generative and discriminative models
- topic models
- semi supervised learning
- representational power
- expectation maximization
- discriminatively trained
- similarity measure
- computer vision