Assessing face and speech consistency for monologue detection in video.
Harriet J. NockGiridharan IyengarChalapathy NetiPublished in: ACM Multimedia (2002)
Keyphrases
- face detection and tracking
- video data
- audio stream
- multimedia
- recognition engine
- speech signal
- video content
- video streams
- face detection
- object detection
- video sequences
- prosodic features
- false positives
- activity detection
- real time
- mouth region
- content based video retrieval
- temporal consistency
- detection accuracy
- detection method
- voice activity detection
- video clips
- complex background
- video indexing
- event detection
- speech synthesis
- human faces
- shot detection
- video frames
- detection algorithm
- digital audio
- person detection
- video analysis
- soccer video
- visual speech
- shot boundary detection
- speech recognition
- space time
- news video
- emotion recognition
- face images
- recognition algorithm