Text Caption Generation Based on Lip Movement of Speaker in Video Using Neural Network.
Dipti PawadeAvani SakhaparaChaitya ShahJigar WalaAnkitmani TripathiBhavikk ShahPublished in: ICACDS (2) (2019)
Keyphrases
- news video
- neural network
- caption text
- text extraction
- text generation
- video retrieval
- video content
- video data
- video database
- video frames
- video sequences
- video search
- multimedia
- natural language descriptions
- back propagation
- video shots
- visual speech
- semantic information
- natural language generation
- information retrieval
- synthesized speech
- neural network model
- video segments
- video streams
- text detection
- visual data
- audio visual
- speech recognition
- text regions
- video analysis
- artificial neural networks
- text mining
- video images
- key frames
- video clips
- visual information
- text to speech
- visual features
- human actions
- hidden markov models
- region based image
- mouth region
- real time