Sams-Net: A Sliced Attention-based Neural Network for Music Source Separation

2019/09/12 by Tingle Li, Li, Tingle, Jiawei Chen +5
Computer Science · #Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Information Retrieval (cs.IR) #Machine Learning (cs.LG) #Music and Audio Processing #Sound (cs.SD) #Speech Recognition and Synthesis #Speech and Audio Processing #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.1909.05746

openalex publication_date 2019/09/12 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Convolutional Neural Network (CNN) or Long short-term memory (LSTM) based models with the input of spectrogram or waveforms are commonly used for deep learning based audio source separation. In this paper, we propose a Sliced Attention-based neural network (Sams-Net) in the spectrogram domain for the music source separation task. It enables spectral feature interactions with multi-head attention mechanism, achieves easier parallel computing and has a larger receptive field compared with LSTMs and CNNs respectively. Experimental results on the MUSDB18 dataset show that the proposed method, with fewer parameters, outperforms most of the state-of-the-art DNN-based methods.

Citations

• WaveNet: A Generative Model for Raw Audio
• Attention U-Net: Learning Where to Look for the Pancreas
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Music Source Separation in the Waveform Domain

Related

• Multi-scale temporal-frequency attention for music source separation
• Atss-Net: Target Speaker Separation via Attention-based Neural Network
• Voice and accompaniment separation in music using self-attention convolutional neural network
• SCNet: Sparse Compression Network for Music Source Separation
• MMDenseLSTM: An efficient combination of convolutional and recurrent neural networks for audio source separation