This article addresses the problem of multichannel audio source separation. We propose a framework where deep neural networks (DNNs) are used to model the source spectra and combined with the classical multichannel Gaussian model to exploit the spatial information. The parameters are estimated in an iterative expectation-maximization (EM) fashion and used to derive a multichannel Wiener filter. We present an extensive experimental study to show the impact of different design choices on the performance of the proposed technique. We consider different cost functions for the training of DNNs, namely the probabilistically motivated Itakura-Saito divergence, and also Kullback-Leibler, Cauchy, mean squared error, and phase-sensitive cost functions. We also study the number of EM iterations and the use of multiple DNNs, where each DNN aims to improve the spectra estimated by the preceding EM iteration. Finally, we present its application to a speech enhancement problem. The experimental results show the benefit of the proposed multichannel approach over a single-channel DNNbased approach and the conventional multichannel nonnegative matrix factorization based iterative EM algorithm.

Music source separation is the task of decomposing music into its constitutive components, e.g., yielding separated stems for the vocals, bass, and drums. Such a separation has many applications ranging from rearranging/repurposing the stems (remixing, repanning, upmixing) to full extraction (karaoke, sample creation, audio restoration). Music separation has a long history of scientific activity as it is known to be a very challenging problem. In recent years, deep learning-based systems-for the first time-yielded high-quality separations that also lead to increased commercial interest. However, until now, no open-source implementation that achieves state-of-the-art results is available. Open-Unmix closes this gap by providing a reference implementation based on deep neural networks. It serves two main purposes. Firstly, to accelerate academic research as Open-Unmix provides implementations for the most popular deep learning frameworks, giving researchers a flexible way to reproduce results. Secondly, we provide a pre-trained model for end users and even artists to try and use source separation. Furthermore, we designed Open-Unmix to be one core component in an open ecosystem on music separation, where we already provide open datasets, software utilities, and open evaluation to foster reproducible research as the basis of future development.

The recent theory of compressive sensing leverages upon the structure of signals to acquire them with much fewer measurements than was previously thought necessary, and certainly well below the traditional Nyquist-Shannon sampling rate. However, most implementations developed to take advantage of this framework revolve around controlling the measurements with carefully engineered material or acquisition sequences. Instead, we use the natural randomness of wave propagation through multiply scattering media as an optimal and instantaneous compressive imaging mechanism. Waves reflected from an object are detected after propagation through a well-characterized complex medium. Each local measurement thus contains global information about the object, yielding a purely analog compressive sensing method. We experimentally demonstrate the effectiveness of the proposed approach for optical imaging by using a 300-micrometer thick layer of white paint as the compressive imaging device. Scattering media are thus promising candidates for designing efficient and compact compressive imagers.