Singing-Voice Separation from Monaural Recordings using Deep Recurrent Neural Networks.
Po-Sen HuangMinje KimMark Hasegawa-JohnsonParis SmaragdisPublished in: ISMIR (2014)
Keyphrases
- recurrent neural networks
- acoustic features
- feed forward
- neural network
- recurrent networks
- echo state networks
- neural model
- artificial neural networks
- reservoir computing
- complex valued
- music information retrieval
- hidden layer
- cascade correlation
- long short term memory
- feedforward neural networks
- input output
- nonlinear dynamic systems
- back propagation