Encoding large array signals into a 3D sound field representation for selective listening point audio based on blind source separation.
Kenta NiwaTakanori NishinoKazuya TakedaPublished in: ICASSP (2008)
Keyphrases
- blind source separation
- independent component analysis
- source separation
- blind separation
- non stationary
- adaptive particle swarm optimization
- signal processing
- negative matrix factorization
- multimedia
- source signals
- audio signal
- speech signal
- mixing matrix
- independent components
- audio features
- sparse representation
- image representation
- representation scheme
- sound source
- factor analysis
- audio visual
- algebraic equations
- eigenvalue decomposition
- neural network