Superposed speech localisation using frequency tracking.
Maxime Le CozJulien PinquierRégine André-ObrechtPublished in: INTERSPEECH (2013)
Keyphrases
- particle filter
- real time
- fundamental frequency
- speech recognition
- mean shift
- kalman filter
- visual tracking
- object tracking
- appearance model
- motion segmentation
- dialogue system
- text to speech
- speaker identification
- endpoint detection
- speech synthesis
- broadcast news
- spoken language
- audio visual
- computer vision
- neural network