Score-Informed Leading Voice Separation from Monaural Audio.
Cyril JoderBjörn W. SchullerPublished in: ISMIR (2012)
Keyphrases
- emotion recognition
- text to speech
- multimedia
- audio visual
- voice activity detection
- prosodic features
- audio signals
- signal processing
- audio stream
- cepstral features
- scoring methods
- data sets
- noisy environments
- multimedia information
- scoring function
- digital video
- visual information
- human computer interaction
- image processing
- genetic algorithm