Video-Driven Speech Reconstruction Using Generative Adversarial Networks.
Konstantinos VougioukasPingchuan MaStavros PetridisMaja PanticPublished in: INTERSPEECH (2019)
Keyphrases
- data driven
- video data
- video sequences
- video content
- network structure
- content based video retrieval
- generative model
- multimedia
- video frames
- video database
- digital audio
- visual data
- speech recognition
- broadcast news
- real time
- visual information
- video shots
- video streams
- audio video
- video clips
- video retrieval
- audio stream
- multimedia data
- image reconstruction
- high resolution
- three dimensional
- social networks
- temporal information
- complex networks
- speech signal
- maximum likelihood
- digital video
- moving objects
- image sequences
- natural language descriptions