Upsampling layers for music source separation.
Jordi PonsJoan SerràSantiago PascualGiulio CengarleDaniel ArteagaDavide ScainiPublished in: CoRR (2021)
Keyphrases
- source separation
- audio features
- music emotion recognition
- blind source separation
- independent component analysis
- audio visual
- music information retrieval
- low level
- denoising
- feature set
- visual features
- single channel
- audio signal
- music retrieval
- simple linear
- sound source
- text data
- image compression
- personalized recommendation
- computer vision
- gaussian process
- hidden markov models
- multi channel
- high level