VoCo: text-based insertion and replacement in audio narration.
Zeyu JinGautham J. MysoreStephen DiVerdiJingwan LuAdam FinkelsteinPublished in: ACM Trans. Graph. (2017)
Keyphrases
- multimedia
- audio visual
- visual information
- audio video
- audio signals
- presentation mode
- visual data
- interactive storytelling
- signal processing
- audio stream
- music score
- digital video
- cross modal
- music scores
- audio files
- database
- automatic transcription
- relational database design
- visual features
- database systems
- image processing
- genetic algorithm
- information retrieval