English
Related papers

Related papers: Music Source Separation with Deep Equilibrium Mode…

200 papers

Implicit models separate the definition of a layer from the description of its solution process. While implicit layers allow features such as depth to adapt to new scenarios and inputs automatically, this adaptivity makes its computational…

Machine Learning · Computer Science 2023-03-06 Avik Pal , Alan Edelman , Christopher Rackauckas

The ability of snapshot compressive imaging (SCI) systems to efficiently capture high-dimensional (HD) data has led to an inverse problem, which consists of recovering the HD signal from the compressed and noisy measurement. While…

Image and Video Processing · Electrical Eng. & Systems 2023-03-01 Yaping Zhao , Siming Zheng , Xin Yuan

Diffusion models excel at producing high-quality samples but naively require hundreds of iterations, prompting multiple attempts to distill the generation process into a faster network. However, many existing approaches suffer from a…

Computer Vision and Pattern Recognition · Computer Science 2024-01-18 Zhengyang Geng , Ashwini Pokle , J. Zico Kolter

We propose a generative framework for multi-track music source separation (MSS) that reformulates the task as conditional discrete token generation. Unlike conventional approaches that directly estimate continuous signals in the time or…

Audio and Speech Processing · Electrical Eng. & Systems 2026-04-20 Pengbo Lyu , Xiangyu Zhao , Chengwei Liu , Haoyin Yan , Xiaotao Liang , Hongyu Wang , Shaofei Xue

We propose a new class of implicit networks, the multiscale deep equilibrium model (MDEQ), suited to large-scale and highly hierarchical pattern recognition domains. An MDEQ directly solves for and backpropagates through the equilibrium…

Machine Learning · Computer Science 2020-11-25 Shaojie Bai , Vladlen Koltun , J. Zico Kolter

In recent years, significant advances have been made in music source separation, with model architectures such as dual-path modeling, band-split modules, or transformer layers achieving comparably good results. However, these models often…

Audio and Speech Processing · Electrical Eng. & Systems 2025-10-09 Yun-Ning , Hung , Igor Pereira , Filip Korzeniowski

A deep equilibrium model (DEQ) is implicitly defined through an equilibrium point of an infinite-depth weight-tied model with an input-injection. Instead of infinite computations, it solves an equilibrium point directly with root-finding…

Machine Learning · Computer Science 2023-03-30 Zenan Ling , Xingyu Xie , Qiuhao Wang , Zongpeng Zhang , Zhouchen Lin

Speech separation (SS) has advanced significantly with neural network-based methods, showing improved performance on signal-level metrics. However, these methods often struggle to maintain speech intelligibility in the separated signals,…

Sound · Computer Science 2026-01-28 Tianhua Li , Chenda Li , Wei Wang , Xin Zhou , Xihui Chen , Jianqing Gao , Yanmin Qian

Music source separation represents the task of extracting all the instruments from a given song. Recent breakthroughs on this challenge have gravitated around a single dataset, MUSDB, only limited to four instrument classes. Larger datasets…

Sound · Computer Science 2021-12-02 Alexandru Mocanu , Benjamin Ricaud , Milos Cernak

This paper addresses the challenges of Hindi speech separation and enhancement using advanced neural network architectures, with a focus on edge devices. We propose a refined approach leveraging the DEMUCS model to overcome limitations of…

Sound · Computer Science 2025-08-25 Arnav Ramamoorthy

We consider the task of optimally fine-tuning pre-trained multilingual models, given small amounts of unlabelled target data and an annotation budget. In this paper, we introduce DEMUX, a framework that prescribes the exact data-points to…

Computation and Language · Computer Science 2023-11-14 Simran Khanuja , Srinivas Gowriraj , Lucio Dery , Graham Neubig

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…

In spite of the progress in music source separation research, the small amount of publicly-available clean source data remains a constant limiting factor for performance. Thus, recent advances in self-supervised learning present a…

Sound · Computer Science 2023-04-06 Ke Chen , Gordon Wichern , François G. Germain , Jonathan Le Roux

In this report, we present our award-winning solutions for the Music Demixing Track of Sound Demixing Challenge 2023. First, we propose TFC-TDF-UNet v3, a time-efficient music source separation model that achieves state-of-the-art results…

Sound · Computer Science 2023-07-24 Minseok Kim , Jun Hyung Lee , Soonyoung Jung

Music source separation (MSS) aims to separate a music recording into multiple musically distinct stems, such as vocals, bass, drums, and more. Recently, deep learning approaches such as convolutional neural networks (CNNs) and recurrent…

Sound · Computer Science 2023-09-12 Wei-Tsung Lu , Ju-Chiang Wang , Qiuqiang Kong , Yun-Ning Hung

Recent approaches for music source separation are almost exclusively based on deep neural networks, mostly employing recurrent neural networks (RNNs). Although RNNs are in many cases superior than other types of deep neural networks for…

Audio and Speech Processing · Electrical Eng. & Systems 2020-07-08 Pyry Pyykkönen , Styliannos I. Mimilakis , Konstantinos Drossos , Tuomas Virtanen

Deep Equilibrium Models (DEQs) are implicit neural networks with fixed points, which have recently gained attention for learning image regularization functionals, particularly in settings involving Gaussian fidelities, where assumptions on…

Optimization and Control · Mathematics 2025-11-19 Christian Daniele , Silvia Villa , Samuel Vaiter , Luca Calatroni

In recent years, rapid progress has been made on the problem of single-channel sound separation using supervised training of deep neural networks. In such supervised approaches, a model is trained to predict the component sources from…

Audio and Speech Processing · Electrical Eng. & Systems 2020-10-27 Scott Wisdom , Efthymios Tzinis , Hakan Erdogan , Ron J. Weiss , Kevin Wilson , John R. Hershey

Many tasks in deep learning involve optimizing over the \emph{inputs} to a network to minimize or maximize some objective; examples include optimization over latent spaces in a generative model to match a target image, or adversarially…

Machine Learning · Computer Science 2021-11-29 Swaminathan Gurumurthy , Shaojie Bai , Zachary Manchester , J. Zico Kolter

Deep Equilibrium (DEQ) Models, an emerging class of implicit models that maps inputs to fixed points of neural networks, are of growing interest in the deep learning community. However, training and applying DEQ models is currently done in…

Machine Learning · Computer Science 2023-10-31 Zhengyang Geng , J. Zico Kolter