Depthwise Separable Convolutions Versus Recurrent Neural Networks for Monaural Singing Voice Separation.
Pyry PyykkönenStylianos Ioannis MimilakisKonstantinos DrossosTuomas VirtanenPublished in: CoRR (2020)
Keyphrases
- audio features
- recurrent neural networks
- music information retrieval
- neural network
- recurrent networks
- feedforward neural networks
- reservoir computing
- neural model
- fourier transform
- complex valued
- artificial neural networks
- feed forward
- echo state networks
- hebbian learning
- long short term memory
- control system
- cascade correlation
- discrete fourier transform
- evolutionary algorithm