Speech-Driven Expressive Talking Lips with Conditional Sequential Generative Adversarial Networks.
Najmeh SadoughiCarlos BussoPublished in: IEEE Trans. Affect. Comput. (2021)
Keyphrases
- data driven
- generative model
- speech recognition
- social networks
- automatic speech recognition
- human faces
- speech signal
- computer networks
- lip reading
- recognition engine
- text to speech
- unsupervised learning
- multi agent
- network analysis
- network structure
- spoken language
- speaker identification
- hidden markov models
- information retrieval