Power-law distribution in encoded MFCC frames of speech, music, and environmental sound signals.
Martín HaroJoan SerràAlvaro CorralPerfecto HerreraPublished in: WWW (Companion Volume) (2012)
Keyphrases
- sound signals
- speech signal
- power law distribution
- speech recognition
- sound source
- audio features
- acoustic features
- power laws
- automatic speech recognition
- speaker identification
- long tail
- power law
- social networks
- scale free
- non stationary
- audio visual
- music information retrieval
- audio signal
- social influence
- multi modal
- pattern recognition
- key frames