Joint Optimization of Masks and Deep Recurrent Neural Networks for Monaural Source Separation.
Po-Sen HuangMinje KimMark Hasegawa-JohnsonParis SmaragdisPublished in: IEEE ACM Trans. Audio Speech Lang. Process. (2015)
Keyphrases
- recurrent neural networks
- joint optimization
- source separation
- blind source separation
- independent component analysis
- neural network
- single channel
- sparse representation
- denoising
- feed forward
- recurrent networks
- edge detection
- temporal structure
- artificial neural networks
- echo state networks
- audio features
- multi channel
- signal processing
- principal component analysis
- regression model
- multi modal
- image classification
- object recognition
- support vector