Content based singing voice source separation via strong conditioning using aligned phonemes.
Gabriel Meseguer-BrocalGeoffroy PeetersPublished in: ISMIR (2020)
Keyphrases
- source separation
- audio features
- blind source separation
- independent component analysis
- text to speech
- denoising
- audio visual
- image retrieval
- speech signal
- single channel
- temporal structure
- image processing
- feature set
- multi modal
- relevance feedback
- multimedia
- text data
- multi channel
- visual features
- music information retrieval
- audio signal
- feature space
- computer vision