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.

No abstract

This paper deals with the problem of audio source separation. To handle the complex and ill-posed nature of the problems of audio source separation, the current state-of-the-art approaches employ deep neural networks to obtain instrumental spectra from a mixture. In this study, we propose a novel network architecture that extends the recently developed densely connected convolutional network (DenseNet), which has shown excellent results on image classification tasks. To deal with the specific problem of audio source separation, an up-sampling layer, block skip connection and banddedicated dense blocks are incorporated on top of DenseNet. The proposed approach takes advantage of long contextual information and outperforms state-of-the-art results on SiSEC 2016 competition by a large margin in terms of signal-to-distortion ratio. Moreover, the proposed architecture requires significantly fewer parameters and considerably less training time compared with other methods.

Deep neural networks have become an indispensable technique for audio source separation (ASS). It was recently reported that a variant of CNN architecture called MM-DenseNet was successfully employed to solve the ASS problem of estimating source amplitudes, and state-of-the-art results were obtained for DSD100 dataset. To further enhance MMDenseNet, here we propose a novel architecture that integrates long short-term memory (LSTM) in multiple scales with skip connections to efficiently model long-term structures within an audio context. The experimental results show that the proposed method outperforms MMDenseNet, LSTM and a blend of the two networks. The number of parameters and processing time of the proposed model are significantly less than those for simple blending. Furthermore, the proposed method yields better results than those obtained using ideal binary masks for a singing voice separation task.

No abstract