SCNet: Sparse Compression Network for Music Source Separation
Authors:
- 14 April 2024
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1276-1280
Abstract
Deep learning-based methods have made significant achievements in music source separation. However, obtaining good results while maintaining a low model complexity remains challenging in super wide-band music source separation. Previous works either overlook the differences in subbands or inadequately address the problem of information loss when generating subband features. In this paper, we propose SCNet, a novel frequency-domain network to explicitly split the spectrogram of the mixture into several subbands and introduce a sparsity-based encoder to model different frequency bands. We use a higher compression ratio on subbands with less information to improve the information density and focus on modeling subbands with more information. In this way, the separation performance can be significantly improved using lower computational consumption. Experiment results show that the proposed model achieves a signal to distortion ratio (SDR) of 9.0 dB on the MUSDB18-HQ dataset without using extra data, which outperforms state-of-the-art methods. Specifically, SCNet’s CPU inference time is only 48% of HT Demucs, one of the previous state-of-the-art models.Keywords
All Related Versions
This publication has 12 references indexed in Scilit:
- Hybrid Transformers for Music Source Separation2023
- TFCnet: Time-Frequency Domain Corrector for Speech Separation2023
- SparseViT: Revisiting Activation Sparsity for Efficient High-Resolution Vision Transformer2023
- Music Source Separation With Band-Split RNNIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2023
- Dual-Path RNN: Efficient Long Sequence Modeling for Time-Domain Single-Channel Speech Separation2020
- Conv-TasNet: Surpassing Ideal Time–Frequency Magnitude Masking for Speech SeparationIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2019
- The 2018 Signal Separation Evaluation Campaign2018
- Improving music source separation based on deep neural networks through data augmentation and network blending2017
- Monoaural Audio Source Separation Using Deep Convolutional Neural Networks2017
- Performance measurement in blind audio source separationIEEE Transactions on Audio, Speech, and Language Processing, 2006