Improving mix-and-separate training in audio-visual sound source separation with an object prior.
Quan NguyenJulius RichterMikko LauriTimo GerkmannSimone FrintropPublished in: ICPR (2020)
Keyphrases
- audio visual
- audio features
- source separation
- multi modal
- audio signal
- sound source
- visual information
- blind source separation
- visual data
- independent component analysis
- training set
- prior knowledge
- high dimensional
- multimedia
- data sets
- temporal structure
- contextual information
- denoising
- moving objects
- multiscale
- computer vision