Detection and Separation of Speech Event Using Audio and Video Information Fusion and Its Application to Robust Speech Interface.
Futoshi AsanoKiyoshi YamamotoIsao HaraJun OgataTakashi YoshimuraYoichi MotomuraNaoyuki IchimuraHideki AsohPublished in: EURASIP J. Adv. Signal Process. (2004)
Keyphrases
- information fusion
- audio stream
- emotion recognition
- broadcast news
- soccer video
- content based video retrieval
- audio visual
- event detection
- digital audio
- audio features
- audio signals
- multimedia
- speech recognition
- text to speech
- data fusion
- audio video
- noisy environments
- video streams
- speaker identification
- video data
- fusion algorithm
- speech signal
- soft computing
- video scene
- visual data
- multi source
- video analysis
- decision level
- video retrieval
- information gathering
- automatic speech recognition
- fusion method
- video sequences
- neural network
- mouth region
- visual speech
- audio signal
- computational intelligence
- fuzzy logic
- decision making