LightSAFT: Lightweight Latent Source Aware Frequency Transform for Source Separation

11/24/2021
by   Yeong-Seok Jeong, et al.
26

Conditioned source separations have attracted significant attention because of their flexibility, applicability and extensionality. Their performance was usually inferior to the existing approaches, such as the single source separation model. However, a recently proposed method called LaSAFT-Net has shown that conditioned models can show comparable performance against existing single-source separation models. This paper presents LightSAFT-Net, a lightweight version of LaSAFT-Net. As a baseline, it provided a sufficient SDR performance for comparison during the Music Demixing Challenge at ISMIR 2021. This paper also enhances the existing LightSAFT-Net by replacing the LightSAFT blocks in the encoder with TFC-TDF blocks. Our enhanced LightSAFT-Net outperforms the previous one with fewer parameters.Conditioned source separations have attracted significant attention because of their flexibility, applicability and extensionality. Their performance was usually inferior to the existing approaches, such as the single source separation model. However, a recently proposed method called LaSAFT-Net has shown that conditioned models can show comparable performance against existing single-source separation models. This paper presents LightSAFT-Net, a lightweight version of LaSAFT-Net. As a baseline, it provided a sufficient SDR performance for comparison during the Music Demixing Challenge at ISMIR 2021.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/05/2023

Hybrid Y-Net Architecture for Singing Voice Separation

This research paper presents a novel deep learning-based neural network ...
research
10/22/2020

LaSAFT: Latent Source Attentive Frequency Transformation for Conditioned Source Separation

Recent deep-learning approaches have shown that Frequency Transformation...
research
03/23/2020

Multi-channel U-Net for Music Source Separation

A fairly straightforward approach for music source separation is to trai...
research
03/23/2020

Multi-task U-Net for Music Source Separation

A fairly straightforward approach for music source separation is to trai...
research
09/15/2023

Music Source Separation Based on a Lightweight Deep Learning Framework (DTTNET: DUAL-PATH TFC-TDF UNET)

Music source separation (MSS) aims to extract 'vocals', 'drums', 'bass' ...
research
02/17/2020

Meta-learning Extractors for Music Source Separation

We propose a hierarchical meta-learning-inspired model for music source ...
research
12/14/2020

Group Communication with Context Codec for Ultra-Lightweight Source Separation

Ultra-lightweight model design is an important topic for the deployment ...

Please sign up or login with your details

Forgot password? Click here to reset