Detection and separation of speech segment using audio and video information fusion.
Futoshi AsanoYoichi MotomuraHideki AsohTakashi YoshimuraNaoyuki IchimuraKiyoshi YamamotoNobuhiko KitawakiSatoshi NakamuraPublished in: INTERSPEECH (2003)
Keyphrases
- information fusion
- emotion recognition
- audio stream
- video scene
- audio visual
- audio video
- digital audio
- soccer video
- multimedia
- broadcast news
- audio signals
- data fusion
- audio features
- content based video retrieval
- temporal segmentation
- fusion algorithm
- information gathering
- video data
- mouth region
- visual data
- fusion model
- video streams
- soft computing
- fusion method
- video analysis
- multi source
- speech recognition
- video sequences
- video frames
- visual information
- real time
- multi sensor information fusion
- speaker identification
- video content
- pattern recognition
- neural network
- text to speech
- video segments
- control system
- knowledge base