Audio Source Separation via Multi-Scale Learning with Dilated Dense U-Nets
Modern audio source separation techniques rely on optimizing sequence model architectures such as, 1D-CNNs, on mixture recordings to generalize well to unseen mixtures. Specifically, recent focus is on time-domain based architectures such as Wave-U-Net which exploit temporal context by extracting multi-scale features. However, the optimality of the feature extraction process in these architectures has not been well investigated. In this paper, we examine and recommend critical architectural changes that forge an optimal multi-scale feature extraction process. To this end, we replace regular $1-$D convolutions with adaptive dilated convolutions that have innate capability of capturing increased context by using large temporal receptive fields. We also investigate the impact of dense connections on the extraction process that encourage feature reuse and better gradient flow. The dense connections between the downsampling and upsampling paths of a U-Net architecture capture multi-resolution information leading to improved temporal modelling. We evaluate the proposed approaches on the MUSDB test dataset. In addition to providing an improved performance over the state-of-the-art, we also provide insights on the impact of different architectural choices on complex data-driven solutions for source separation.
Code (0)
등록된 구현이 없습니다.
Tasks
Audio Source SeparationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Dilated Convolution with Dilated GRU for Music Source Separation
Stacked dilated convolutions used in Wavenet have been shown effective for generating high-quality audios. By replacing pooling/striding with dilation in convolution layers, they can preserve high-resolution information …
Music Source SeparationD3Net: Densely connected multidilated DenseNet for music source separation
Music source separation involves a large input field to model a long-term dependence of an audio signal. Previous convolutional neural network (CNN)-based approaches address the large input field modeling using sequentia…
Music Source SeparationDomestic Activities Classification from Audio Recordings Using Multi-scale Dilated Depthwise Separable Convolutional Network
Domestic activities classification (DAC) from audio recordings aims at classifying audio recordings into pre-defined categories of domestic activities, which is an effective way for estimation of daily activities perform…
The Whole Is Greater than the Sum of Its Parts: Improving Music Source Separation by Bridging Network
This paper presents the crossing scheme (X-scheme) for improving the performance of deep neural network (DNN)-based music source separation (MSS) with almost no increasing calculation cost. It consists of three component…
Music Source SeparationDensely connected multidilated convolutional networks for dense prediction tasks
Tasks that involve high-resolution dense prediction require a modeling of both local and global patterns in a large input field. Although the local and global structures often depend on each other and their simultaneous …
Audio Source SeparationMusic Source SeparationSemantic Segmentation