Audio Source Separation with Discriminative Scattering Networks
This work addresses the challenge of exploiting temporal dependencies in audio signals for source separation, which is incremental as it builds on existing methods like NMF and deep learning.
The authors tackled the problem of single-channel audio source separation by modeling signals with a multi-resolution time-frequency representation using wavelet scattering operators, which improved separation results over fixed-resolution methods, particularly when integrated with Non-Negative Matrix Factorization and deep neural networks.
In this report we describe an ongoing line of research for solving single-channel source separation problems. Many monaural signal decomposition techniques proposed in the literature operate on a feature space consisting of a time-frequency representation of the input data. A challenge faced by these approaches is to effectively exploit the temporal dependencies of the signals at scales larger than the duration of a time-frame. In this work we propose to tackle this problem by modeling the signals using a time-frequency representation with multiple temporal resolutions. The proposed representation consists of a pyramid of wavelet scattering operators, which generalizes Constant Q Transforms (CQT) with extra layers of convolution and complex modulus. We first show that learning standard models with this multi-resolution setting improves source separation results over fixed-resolution methods. As study case, we use Non-Negative Matrix Factorizations (NMF) that has been widely considered in many audio application. Then, we investigate the inclusion of the proposed multi-resolution setting into a discriminative training regime. We discuss several alternatives using different deep neural network architectures.