Multi-Speaker Emotion Conversion via Latent Variable Regularization and a Chained Encoder-Decoder-Predictor Network.
Ravi ShankarHsi-Wei HsiehNicolas CharonArchana VenkataramanPublished in: INTERSPEECH (2020)
Keyphrases
- latent variables
- low complexity
- successive approximation
- video codec
- probabilistic model
- decoding process
- latent variable models
- distributed video coding
- error control
- network structure
- prior knowledge
- information retrieval
- motion estimation
- random variables
- video sequences
- bayesian networks
- emotion recognition
- turbo codes