Search Results for author:
Found 112 papers, 49 papers with code
AudioSR: Versatile Audio Super-resolution at Scale
Audio super-resolution is a fundamental task that predicts high-frequency components for low-resolution audio, enhancing audio quality in digital applications.
MusPy: A Toolkit for Symbolic Music Generation
MusPy provides easy-to-use tools for essential components in a music generation system, including dataset management, data I/O, data preprocessing and model evaluation.
HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection
To combat these problems, we introduce HTS-AT: an audio transformer with a hierarchical structure to reduce the model size and training time.
Ranked #4 on
Sound Event Detection
on DESED
POP909: A Pop-song Dataset for Music Arrangement Generation
The main body of the dataset contains the vocal melody, the lead instrument melody, and the piano accompaniment for each song in MIDI format, which are aligned to the original audio files.
Zero-shot Audio Source Separation through Query-based Learning from Weakly-labeled Data
Our approach uses a single model for source separation of multiple sound types, and relies solely on weakly-labeled data for training.
Ranked #1 on
Audio Source Separation
on AudioSet
Multitrack Music Transformer
Existing approaches for generating multitrack music with transformer models have been limited in terms of the number of instruments, the length of the music segments and slow inference.
MusicLDM: Enhancing Novelty in Text-to-Music Generation Using Beat-Synchronous Mixup Strategies
Diffusion models have shown promising results in cross-modal generation tasks, including text-to-image and text-to-audio generation.
The Song Describer Dataset: a Corpus of Audio Captions for Music-and-Language Evaluation
We introduce the Song Describer dataset (SDD), a new crowdsourced corpus of high-quality audio-caption pairs, designed for the evaluation of music-and-language models.
Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding
This approach is characterized by a two-stage process: drafting and verification.
ShopSign: a Diverse Scene Text Dataset of Chinese Shop Signs in Street Views
Hence, we collect and annotate the ShopSign dataset to advance research in Chinese scene text detection and recognition.
Unsupervised Domain Adaptation via Structurally Regularized Deep Clustering
To alleviate this risk, we are motivated by the assumption of structural domain similarity, and propose to directly uncover the intrinsic target discrimination via discriminative clustering of target data.
Music SketchNet: Controllable Music Generation via Factorized Representations of Pitch and Rhythm
Drawing an analogy with automatic image completion systems, we propose Music SketchNet, a neural network framework that allows users to specify partial musical ideas guiding automatic music generation.
3D AffordanceNet: A Benchmark for Visual Object Affordance Understanding
The ability to understand the ways to interact with objects from visual cues, a. k. a.
Ranked #1 on
Affordance Detection
on 3D AffordanceNet
Cascading Convolutional Color Constancy
Regressing the illumination of a scene from the representations of object appearances is popularly adopted in computational color constancy.
TONet: Tone-Octave Network for Singing Melody Extraction from Polyphonic Music
In this paper, we propose TONet, a plug-and-play model that improves both tone and octave perceptions by leveraging a novel input representation and a novel network architecture.
Feature Importance Ranking for Deep Learning
During learning, the operator is trained for a supervised learning task via optimal feature subset candidates generated by the selector that learns predicting the learning performance of the operator working on different optimal subset candidates.
Sparse Steerable Convolutions: An Efficient Learning of SE(3)-Equivariant Features for Estimation and Tracking of Object Poses in 3D Space
In this paper, we propose a novel design of Sparse Steerable Convolution (SS-Conv) to address the shortcoming; SS-Conv greatly accelerates steerable convolution with sparse tensors, while strictly preserving the property of SE(3)-equivariance.
Geometry-Aware Generation of Adversarial Point Clouds
Regularizing the targeted attack loss with our proposed geometry-aware objectives results in our proposed method, Geometry-Aware Adversarial Attack ($GeoA^3$).
Pyramid: A Layered Model for Nested Named Entity Recognition
Its hidden state at layer l represents an l-gram in the input text, which is labeled only if its corresponding text region represents a complete entity mention.
Ranked #1 on
Nested Named Entity Recognition
on NNE
Geometry-Aware Self-Training for Unsupervised Domain Adaptationon Object Point Clouds
The point cloud representation of an object can have a large geometric variation in view of inconsistent data acquisition procedure, which thus leads to domain discrepancy due to diverse and uncontrollable shape representation cross datasets.
Geometry-Aware Self-Training for Unsupervised Domain Adaptation on Object Point Clouds
The point cloud representation of an object can have a large geometric variation in view of inconsistent data acquisition procedure, which thus leads to domain discrepancy due to diverse and uncontrollable shape representation cross datasets.
Fine-Grained Object Classification via Self-Supervised Pose Alignment
Semantic patterns of fine-grained objects are determined by subtle appearance difference of local parts, which thus inspires a number of part-based methods.
Towards Improving Harmonic Sensitivity and Prediction Stability for Singing Melody Extraction
In deep learning research, many melody extraction models rely on redesigning neural network architectures to improve performance.
A Framework for End-to-End Learning on Semantic Tree-Structured Data
In this paper, we propose a novel framework for end-to-end learning on generic semantic tree-structured data of arbitrary topology and heterogeneous data types, such as data expressed in JSON, XML and so on.
BiCo-Net: Regress Globally, Match Locally for Robust 6D Pose Estimation
Inspired by the success of point-pair features, the goal of this paper is to recover the 6D pose of an object instance segmented from RGB-D images by locally matching pairs of oriented points between the model and camera space.
SkipBERT: Efficient Inference with Shallow Layer Skipping
In this paper, we propose SkipBERT to accelerate BERT inference by skipping the computation of shallow layers.
Continuous Melody Generation via Disentangled Short-Term Representations and Structural Conditions
Automatic music generation is an interdisciplinary research topic that combines computational creativity and semantic analysis of music to create automatic machine improvisations.
Quasi-Balanced Self-Training on Noise-Aware Synthesis of Object Point Clouds for Closing Domain Gap
Such a challenge of Simulation-to-Reality (Sim2Real) domain gap could be mitigated via learning algorithms of domain adaptation; however, we argue that generation of synthetic point clouds via more physically realistic rendering is a powerful alternative, as systematic non-uniform noise patterns can be captured.
Convolutional Fine-Grained Classification with Self-Supervised Target Relation Regularization
Such target coding schemes are less flexible to model inter-class correlation and are sensitive to sparse and imbalanced data distribution as well.
GLIB: Towards Automated Test Oracle for Graphically-Rich Applications
We perform an evaluation of \texttt{GLIB} on 20 real-world game apps (with bug reports available) and the result shows that \texttt{GLIB} can achieve 100\% precision and 99. 5\% recall in detecting non-crashing bugs such as game GUI glitches.
Towards Uncovering the Intrinsic Data Structures for Unsupervised Domain Adaptation using Structurally Regularized Deep Clustering
To address this issue, we are motivated by a UDA assumption of structural similarity across domains, and propose to directly uncover the intrinsic target discrimination via constrained clustering, where we constrain the clustering solutions using structural source regularization that hinges on the very same assumption.
CARAT: Contrastive Feature Reconstruction and Aggregation for Multi-Modal Multi-Label Emotion Recognition
The challenge of MMER is how to effectively capture discriminative features for multiple labels from heterogeneous data.
Effective Slot Filling via Weakly-Supervised Dual-Model Learning
By using some particular weakly-labeled data, namely the plain phrases included in sentences, we propose a weaklysupervised slot filling approach.
Goal Exploration Augmentation via Pre-trained Skills for Sparse-Reward Long-Horizon Goal-Conditioned Reinforcement Learning
In GCRL, exploring novel sub-goals is essential for the agent to ultimately find the pathway to the desired goal.
An Interpretable MRI Reconstruction Network with Two-grid-cycle Correction and Geometric Prior Distillation
Although existing deep learning compressed-sensing-based Magnetic Resonance Imaging (CS-MRI) methods have achieved considerably impressive performance, explainability and generalizability continue to be challenging for such methods since the transition from mathematical analysis to network design not always natural enough, often most of them are not flexible enough to handle multi-sampling-ratio reconstruction assignments.
Car Type Recognition with Deep Neural Networks
In this paper we study automatic recognition of cars of four types: Bus, Truck, Van and Small car.
CAD-PU: A Curvature-Adaptive Deep Learning Solution for Point Set Upsampling
Point set is arguably the most direct approximation of an object or scene surface, yet its practical acquisition often suffers from the shortcoming of being noisy, sparse, and possibly incomplete, which restricts its use for a high-quality surface recovery.
Manifold-Aware Self-Training for Unsupervised Domain Adaptation on Regressing 6D Object Pose
Domain gap between synthetic and real data in visual regression (e. g. 6D pose estimation) is bridged in this paper via global feature alignment and local refinement on the coarse classification of discretized anchor classes in target space, which imposes a piece-wise target manifold regularization into domain-invariant representation learning.
Nest-DGIL: Nesterov-optimized Deep Geometric Incremental Learning for CS Image Reconstruction
In the image restoration step, a cascade geometric incremental learning module is designed to compensate for missing texture information from different geometric spectral decomposition domains.
Learning to Play General Video-Games via an Object Embedding Network
Deep reinforcement learning (DRL) has proven to be an effective tool for creating general video-game AI.
Graph Contrastive Learning with Implicit Augmentations
Existing graph contrastive learning methods rely on augmentation techniques based on random perturbations (e. g., randomly adding or dropping edges and nodes).
On the Use of Sparse Filtering for Covariate Shift Adaptation
We provide a theoretical analysis of sparse filtering by evaluating the conditions required to perform covariate shift adaptation.
The Effect of Explicit Structure Encoding of Deep Neural Networks for Symbolic Music Generation
With recent breakthroughs in artificial neural networks, deep generative models have become one of the leading techniques for computational creativity.
ShuffleMix: Improving Representations via Channel-Wise Shuffle of Interpolated Hidden States
Inspired by good robustness of alternative dropout strategies against over-fitting on limited patterns of training samples, this paper introduces a novel concept of ShuffleMix -- Shuffle of Mixed hidden features, which can be interpreted as a kind of dropout operation in feature space.
Improving Deep Representation Learning via Auxiliary Learnable Target Coding
Deep representation learning is a subfield of machine learning that focuses on learning meaningful and useful representations of data through deep neural networks.
Three-Stream Convolutional Networks for Video-based Person Re-Identification
This paper aims to develop a new architecture that can make full use of the feature maps of convolutional networks.
Convolutional Low-Resolution Fine-Grained Classification
Successful fine-grained image classification methods learn subtle details between visually similar (sub-)classes, but the problem becomes significantly more challenging if the details are missing due to low resolution.
Multi-Label Zero-Shot Human Action Recognition via Joint Latent Ranking Embedding
Our framework holistically tackles the issue of unknown temporal boundaries between different actions for multi-label learning and exploits the side information regarding the semantic relationship between different human actions for knowledge transfer.
Generalized Multi-view Embedding for Visual Recognition and Cross-modal Retrieval
In this paper, the problem of multi-view embedding from different visual cues and modalities is considered.
Towards Understanding Sparse Filtering: A Theoretical Perspective
In this paper we present a theoretical analysis to understand sparse filtering, a recent and effective algorithm for unsupervised learning.
Alternative Semantic Representations for Zero-Shot Human Action Recognition
A proper semantic representation for encoding side information is key to the success of zero-shot learning.
Ranked #22 on
Zero-Shot Action Recognition
on UCF101
Zero-Shot Visual Recognition via Bidirectional Latent Embedding
In the top-down stage, semantic representations of unseen-class labels in a given label vocabulary are then embedded to the same latent space to preserve the semantic relatedness between all different classes via our proposed semi-supervised Sammon mapping with the guidance of landmarks.
Implicit Gradient Neural Networks with a Positive-Definite Mass Matrix for Online Linear Equations Solving
Motivated by the advantages achieved by implicit analogue net for solving online linear equations, a novel implicit neural model is designed based on conventional explicit gradient neural networks in this letter by introducing a positive-definite mass matrix.
Deep Structured-Output Regression Learning for Computational Color Constancy
Computational color constancy that requires esti- mation of illuminant colors of images is a fundamental yet active problem in computer vision, which can be formulated into a regression problem.
Deploying learning materials to game content for serious education game development: A case study
Unlike previous work where experts in education have to be used heavily, we proposed a novel approach that works toward minimizing the efforts of education experts in mapping learning materials to content space.
Learning Contextualized Music Semantics from Tags via a Siamese Network
We conduct experiments on three public music tag collections -namely, CAL500, MagTag5K and Million Song Dataset- and compare our approach to a number of state-of-the-art semantics learning approaches.
Multi-Label Zero-Shot Learning via Concept Embedding
Thus, our approach allows both seen and unseen labels during the concept embedding learning to be used in the aforementioned instance mapping, which makes multi-label ZSL more flexible and suitable for real applications.
Efficient Feature-based Image Registration by Mapping Sparsified Surfaces
For each high resolution image or video frame, we compute an optimal coarse triangulation which captures the important features of the image.
Learning Constructive Primitives for Online Level Generation and Real-time Content Adaptation in Super Mario Bros
Also the adaptive content can be generated in real time by dynamically selecting proper constructive primitives via an adaptation criterion, e. g., dynamic difficulty adjustment (DDA).
A Total Fractional-Order Variation Model for Image Restoration with Non-homogeneous Boundary Conditions and its Numerical Solution
In this paper we analyze and test a fractional-order derivative based total $\alpha$-order variation model, which can outperform the currently popular high order regularization models.
Learning Contextualized Semantics from Co-occurring Terms via a Siamese Architecture
By means of pattern aggregation and probabilistic topic models, our Siamese architecture captures contextualized semantics from the co-occurring descriptive terms via unsupervised learning, which leads to a concept embedding space of the terms in context.
A novel variational model for image registration using Gaussian curvature
Image registration is one important task in many image processing applications.
Rapid Skill Capture in a First-Person Shooter
Various aspects of computer game design, including adaptive elements of game levels, characteristics of 'bot' behavior, and player matching in multiplayer games, would ideally be sensitive to a player's skill level.
Learning-Based Procedural Content Generation
Procedural content generation (PCG) has recently become one of the hottest topics in computational intelligence and AI game researches.
Transferable Positive/Negative Speech Emotion Recognition via Class-wise Adversarial Domain Adaptation
Speech emotion recognition plays an important role in building more intelligent and human-like agents.
Intervention Aided Reinforcement Learning for Safe and Practical Policy Optimization in Navigation
We built neural networks as our policy to map sensor readings to control signals on the UAV.
Extracting Speaker-Specific Information with a Regularized Siamese Deep Network
Speech conveys different yet mixed information ranging from linguistic to speaker-specific components, and each of them should be exclusively used in a specific task.
Regularized Boost for Semi-Supervised Learning
Semi-supervised inductive learning concerns how to learn a decision rule from a data set containing both labeled and unlabeled data.
Tooth morphometry using quasi-conformal theory
We deploy our framework on a dataset of human premolars to analyze the tooth shape variation among genders and ancestries.
Cumulative Attribute Space for Age and Crowd Density Estimation
A number of computer vision problems such as human age estimation, crowd density estimation and body/face pose (view angle) estimation can be formulated as a regression problem by learning a mapping function between a high dimensional vector-formed feature input and a scalarvalued output.
Unsupervised Visual Alignment With Similarity Graphs
In this work, we adopt the feature basedapproach, but to overcome the aforementioned drawbacks define visual similarity as an assignment problem which is solved by fast approximation and non-linear optimization. From pair-wise image similarities we construct an image graph which is used to step-wise align,``morph'', an image to another by graph traveling.
Recurrent Color Constancy
We introduce a novel formulation of temporal color constancy which considers multiple frames preceding the frame for which illumination is estimated.
Semi-Supervised Few-Shot Learning for Dual Question-Answer Extraction
In this paper, we redefine the problem as question-answer extraction, and present SAMIE: Self-Asking Model for Information Ixtraction, a semi-supervised model which dually learns to ask and to answer questions by itself.
Capturing Evolution Genes for Time Series Data
The modeling of time series is becoming increasingly critical in a wide variety of applications.
Fast Fourier Color Constancy and Grayness Index for ISPA Illumination Estimation Challenge
We briefly introduce two submissions to the Illumination Estimation Challenge, in the Int'l Workshop on Color Vision, affiliated to the 11th Int'l Symposium on Image and Signal Processing and Analysis.
Learning-Based Video Game Development in MLP@UoM: An Overview
In general, video games not only prevail in entertainment but also have become an alternative methodology for knowledge learning, skill acquisition and assistance for medical treatment as well as health care in education, vocational/military training and medicine.
Towards Further Understanding of Sparse Filtering via Information Bottleneck
In this paper we examine a formalization of feature distribution learning (FDL) in information-theoretic terms relying on the analytical approach and on the tools already used in the study of the information bottleneck (IB).
W-PoseNet: Dense Correspondence Regularized Pixel Pair Pose Regression
Solving 6D pose estimation is non-trivial to cope with intrinsic appearance and shape variation and severe inter-object occlusion, and is made more challenging in light of extrinsic large illumination changes and low quality of the acquired data under an uncontrolled environment.
Ranked #1 on
6D Pose Estimation using RGBD
on LineMOD
(Mean ADD-S metric)
Improving Semantic Analysis on Point Clouds via Auxiliary Supervision of Local Geometric Priors
Existing deep learning algorithms for point cloud analysis mainly concern discovering semantic patterns from global configuration of local geometries in a supervised learning manner.
Compositional Few-Shot Recognition with Primitive Discovery and Enhancing
Inspired by such capability of humans, to imitate humans' ability of learning visual primitives and composing primitives to recognize novel classes, we propose an approach to FSL to learn a feature representation composed of important primitives, which is jointly trained with two parts, i. e. primitive discovery and primitive enhancing.
MVLidarNet: Real-Time Multi-Class Scene Understanding for Autonomous Driving Using Multiple Views
We show that our multi-view, multi-stage, multi-class approach is able to detect and classify objects while simultaneously determining the drivable space using a single LiDAR scan as input, in challenging scenes with more than one hundred vehicles and pedestrians at a time.
A Generalized Asymmetric Dual-front Model for Active Contours and Image Segmentation
The Voronoi diagram-based dual-front active contour models are known as a powerful and efficient way for addressing the image segmentation and domain partitioning problems.
LINDT: Tackling Negative Federated Learning with Local Adaptation
On occasion of NFL recovery, the framework makes adaptation to the federated model on each client's local data by learning a Layer-wise Intertwined Dual-model.
Catalytically Potent and Selective Clusterzymes for Modulation of Neuroinflammation Through Single-Atom Substitutions
Emerging artificial enzymes with reprogrammed and augmented catalytic activity and substrate selectivity have long been pursued with sustained efforts.
Biological Physics Medical Physics
Classification of Single-View Object Point Clouds
By adapting existing ModelNet40 and ScanNet datasets to the single-view, partial setting, experiment results can verify the necessity of object pose estimation and superiority of our PAPNet to existing classifiers.
Label-Efficient Point Cloud Semantic Segmentation: An Active Learning Approach
Deep learning models are the state-of-the-art methods for semantic point cloud segmentation, the success of which relies on the availability of large-scale annotated datasets.
MAX Phase Zr2SeC and Its Thermal Conduction Behavior
The elemental diversity is crucial to screen out ternary MAX phases with outstanding properties via tuning of bonding types and strength between constitutive atoms.
Materials Science
Neural-to-Tree Policy Distillation with Policy Improvement Criterion
The empirical results show that the proposed method can preserve a higher cumulative reward than behavior cloning and learn a more consistent policy to the original one.
Real-Time Vanishing Point Detector Integrating Under-Parameterized RANSAC and Hough Transform
We propose a novel approach that integrates under-parameterized RANSAC (UPRANSAC) with Hough Transform to detect vanishing points (VPs) from un-calibrated monocular images.
Geometry-aware Generation of Adversarial and Cooperative Point Clouds
Recent studies show that machine learning models are vulnerable to adversarial examples.
Using Deep Image Prior to Assist Variational Selective Segmentation Deep Learning Algorithms
Recently, it was shown in the Deep Image Prior work that the explicit regularisation in a model can be removed and replaced by the implicit regularisation captured by the architecture of a neural network.
Zero-shot Audio Source Separation through Query-based Learningfrom Weakly-labeled Data
Our approach uses a single model for source separation of multiple sound types, and relies solely on weakly-labeled data for training.
Fast Multi-grid Methods for Minimizing Curvature Energy
In this paper, we propose fast multi-grid algorithms for minimizing both mean curvature and Gaussian curvature energy functionals without sacrificing accuracy for efficiency.
BYTECOVER2: TOWARDS DIMENSIONALITY REDUCTION OF LATENT EMBEDDING FOR EFFICIENT COVER SONG IDENTIFICATION
Convolutional neural network (CNN)-based methods have dominated the recent research of cover song identification (CSI).
Ranked #1 on
Cover song identification
on SHS100K-TEST
Fisher Matrix Based Fault Detection for PMUs Data in Power Grids
Firstly, the fault detection matrix is constructed and the event detection problem is reformatted as a two-sample covariance matrices test problem.
NVRadarNet: Real-Time Radar Obstacle and Free Space Detection for Autonomous Driving
To this end, we present NVRadarNet, a deep neural network (DNN) that detects dynamic obstacles and drivable free space using automotive RADAR sensors.
An Efficient Semi-Automated Scheme for Infrastructure LiDAR Annotation
Specifically, we introduce a human-in-the-loop schema in which annotators recursively fix and refine annotations imperfectly predicted by our tool and incrementally add them to the training dataset to obtain better SOT and MOT models.
Deep Operator Learning Lessens the Curse of Dimensionality for PDEs
Deep neural networks (DNNs) have achieved remarkable success in numerous domains, and their application to PDE-related problems has been rapidly advancing.
Closed-Loop Transcription via Convolutional Sparse Coding
Our method is arguably the first to demonstrate that a concatenation of multiple convolution sparse coding/decoding layers leads to an interpretable and effective autoencoder for modeling the distribution of large-scale natural image datasets.
Towards Solving Fuzzy Tasks with Human Feedback: A Retrospective of the MineRL BASALT 2022 Competition
To facilitate research in the direction of fine-tuning foundation models from human feedback, we held the MineRL BASALT Competition on Fine-Tuning from Human Feedback at NeurIPS 2022.
Pac-HuBERT: Self-Supervised Music Source Separation via Primitive Auditory Clustering and Hidden-Unit BERT
In this paper, we propose a self-supervised learning framework for music source separation inspired by the HuBERT speech representation model.
Weakly supervised segmentation with point annotations for histopathology images via contrast-based variational model
Image segmentation is a fundamental task in the field of imaging and vision.
TC-GAT: Graph Attention Network for Temporal Causality Discovery
The present study explores the intricacies of causal relationship extraction, a vital component in the pursuit of causality knowledge.
SwinFSR: Stereo Image Super-Resolution using SwinIR and Frequency Domain Knowledge
Stereo Image Super-Resolution (stereoSR) has attracted significant attention in recent years due to the extensive deployment of dual cameras in mobile phones, autonomous vehicles and robots.
Deep Partial Multi-Label Learning with Graph Disambiguation
In partial multi-label learning (PML), each data example is equipped with a candidate label set, which consists of multiple ground-truth labels and other false-positive labels.
A Bi-variant Variational Model for Diffeomorphic Image Registration with Relaxed Jacobian Determinant Constraints
In this paper, we propose a new bi-variant diffeomorphic image registration model that introduces a soft constraint on the Jacobian equation $\det(\nabla\bm{\varphi}(\bm{x})) = f(\bm{x}) > 0$.
Super-Resolution Surface Reconstruction from Few Low-Resolution Slices
In many imaging applications where segmented features (e. g. blood vessels) are further used for other numerical simulations (e. g. finite element analysis), the obtained surfaces do not have fine resolutions suitable for the task.
Adopting Dynamic VAR Compensators to Mitigate PV Impacts on Unbalanced Distribution Systems
However, the effectiveness of this scheme is not well documented, and there is limited literature on alternative control and placement schemes that can maximize the effective use of a DVC.
Bias Resilient Multi-Step Off-Policy Goal-Conditioned Reinforcement Learning
In goal-conditioned reinforcement learning (GCRL), sparse rewards present significant challenges, often obstructing efficient learning.
ADAPT: Alzheimer Diagnosis through Adaptive Profiling Transformers
Automated diagnosis of Alzheimer Disease(AD) from brain imaging, such as magnetic resonance imaging (MRI), has become increasingly important and has attracted the community to contribute many deep learning methods.
FL-GUARD: A Holistic Framework for Run-Time Detection and Recovery of Negative Federated Learning
Federated learning (FL) is a promising approach for learning a model from data distributed on massive clients without exposing data privacy.
Music Enhancement with Deep Filters: A Technical Report for The ICASSP 2024 Cadenza Challenge
In this challenge, we disentangle the deep filters from the original DeepfilterNet and incorporate them into our Spec-UNet-based network to further improve a hybrid Demucs (hdemucs) based remixing pipeline.
