Hybrid Y-Net Architecture for Singing Voice Separation
Sound
2023-03-07 v1 Machine Learning
Audio and Speech Processing
Abstract
This research paper presents a novel deep learning-based neural network architecture, named Y-Net, for achieving music source separation. The proposed architecture performs end-to-end hybrid source separation by extracting features from both spectrogram and waveform domains. Inspired by the U-Net architecture, Y-Net predicts a spectrogram mask to separate vocal sources from a mixture signal. Our results demonstrate the effectiveness of the proposed architecture for music source separation with fewer parameters. Overall, our work presents a promising approach for improving the accuracy and efficiency of music source separation.
Cite
@article{arxiv.2303.02599,
title = {Hybrid Y-Net Architecture for Singing Voice Separation},
author = {Rashen Fernando and Pamudu Ranasinghe and Udula Ranasinghe and Janaka Wijayakulasooriya and Pantaleon Perera},
journal= {arXiv preprint arXiv:2303.02599},
year = {2023}
}
Comments
Submitted for EUSIPCO23: 5 Pages, 7 figures