Source Separation and Depthwise Separable Convolutions for Computer Audition
Given recent advances in deep music source separation, we propose a feature representation method that combines source separation with a state-of-the-art representation learning technique that is suitably repurposed for computer audition (i.e. machine listening). We train a depthwise separable convolutional neural network on a challenging electronic dance music (EDM) data set and compare its performance to convolutional neural networks operating on both source separated and standard spectrograms. It is shown that source separation improves classification performance in a limited-data setting compared to the standard single spectrogram approach.
Code (0)
등록된 구현이 없습니다.
Tasks
Music Source SeparationRepresentation LearningSimilar Papers 제목 키워드 기반
Depthwise Separable Convolutions Versus Recurrent Neural Networks for Monaural Singing Voice Separation
Recent approaches for music source separation are almost exclusively based on deep neural networks, mostly employing recurrent neural networks (RNNs). Although RNNs are in many cases superior than other types of deep neu…
Music Source SeparationDesign and Scaffolded Training of an Efficient DNN Operator for Computer Vision on the Edge
Massively parallel systolic arrays and resource-efficient depthwise separable convolutions are two promising techniques to accelerate DNN inference on the edge. Interestingly, their combination is inefficient: Computatio…
Neural Architecture SearchHigh-Throughput Blind Co-Channel Interference Cancellation for Edge Devices Using Depthwise Separable Convolutions, Quantization, and Pruning
Co-channel interference cancellation (CCI) is the process used to reduce interference from other signals using the same frequency channel, thereby enhancing the performance of wireless communication systems. An improveme…
blind source separationComputational EfficiencyQuantizationNetwork Decoupling: From Regular to Depthwise Separable Convolutions
Depthwise separable convolution has shown great efficiency in network design, but requires time-consuming training procedure with full training-set available. This paper first analyzes the mathematical relationship betwe…
object-detectionObject DetectionDepthwiseGANs: Fast Training Generative Adversarial Networks for Realistic Image Synthesis
Recent work has shown significant progress in the direction of synthetic data generation using Generative Adversarial Networks (GANs). GANs have been applied in many fields of computer vision including text-to-image conv…
Image GenerationSuper-ResolutionSynthetic Data Generation