Adaptation of Bayesian Models for Single-Channel Source Separation and its Application to Voice/Music Separation in Popular Songs.
Alexey OzerovPierrick PhilippeFrédéric BimbotRémi GribonvalPublished in: IEEE Trans. Speech Audio Process. (2007)
Keyphrases
- source separation
- single channel
- audio features
- sound source
- music information retrieval
- music retrieval
- multi channel
- audio visual
- visual features
- speech signal
- low level
- independent component analysis
- real environment
- wavelet decomposition
- machine learning
- signal processing
- feature set
- multiresolution
- speech recognition
- prior knowledge
- multiscale