Video-Driven Speech Reconstruction using Generative Adversarial Networks.
Konstantinos VougioukasPingchuan MaStavros PetridisMaja PanticPublished in: CoRR (2019)
Keyphrases
- video data
- data driven
- video streams
- video sequences
- broadcast news
- speech recognition
- three dimensional
- image reconstruction
- high resolution
- video analysis
- video content
- generative model
- audio video
- content based video retrieval
- multimedia
- multi agent
- video database
- audio signals
- reconstruction method
- real time
- digital audio
- language model
- video clips
- visual data
- key frames
- multimedia data
- dialogue system
- spoken language
- video frames
- discrete tomography
- probabilistic model
- feature vectors
- social networks