Deep Variational Generative Models for Audio-Visual Speech Separation.
Viet-Nhat NguyenMostafa SadeghiElisa RicciXavier Alameda-PinedaPublished in: MLSP (2021)
Keyphrases
- generative model
- visual speech
- hidden markov models
- speaker identification
- probabilistic model
- noisy environments
- audio signals
- discriminative models
- discriminative learning
- mixture model
- deep belief networks
- acoustic features
- em algorithm
- audio signal
- speech recognition
- speech signal
- topic models
- optical flow
- prior knowledge
- video signals
- broadcast news
- image segmentation
- clustering algorithm
- semi supervised
- text to speech
- object categories
- multi modal
- expectation maximization
- video sequences