Improving Singing Voice Separation With The Wave-u-net Using Minimum Hyperspherical Energy

Abstract

In recent years, deep learning has surpassed traditional approaches to the problem of singing voice separation. The Wave-U-Net is a recent deep network architecture that operates directly on the time domain. The standard Wave-U-Net is trained with data augmentation and early stopping to prevent overfitting. Minimum hyperspherical energy (MHE) regularization has recently proven to increase generalization in image classification problems by encouraging a diversified filter configuration. In this work, we apply MHE regularization to the 1D filters of the Wave-U-Net. We evaluated this approach for separating the vocal part from mixed music audio recordings on the MUSDB18 dataset. We found that adding MHE regularization to the loss function consistently improves singing voice separation, as measured in the Signal to Distortion Ratio on test recordings, leading to the current best time-domain system for singing voice extraction.

Stats

• citations8
• S2 citations—
• github stars0
• HF likes0
• heat score7.16
• arxiv keyperezlapillo2019improving

Related papers

• Improving Singing Voice Separation Using Deep U-net And Wave-u-net With Data Augmentation (2019)10.35
• Htmd-net: A Hybrid Masking-denoising Approach To Time-domain Monaural Singing Voice Separation (2021)2.26
• Improved Speech Enhancement With The Wave-u-net (2018)0.00
• Wave-u-net: A Multi-scale Neural Network For End-to-end Audio Source Separation (2018)0.00
• Depthwise Separable Convolutions Versus Recurrent Neural Networks For Monaural Singing Voice Separation (2020)0.00
• Revisiting Representation Learning For Singing Voice Separation With Sinkhorn Distances (2020)0.00
• A Recurrent Encoder-decoder Approach With Skip-filtering Connections For Monaural Singing Voice Separation (2017)9.41
• Singing Voice Separation Using A Deep Convolutional Neural Network Trained By Ideal Binary Mask And Cross Entropy (2018)11.19