Back to Ear: Perceptually Driven High Fidelity Music Reconstruction

• URL: http://arxiv.org/abs/2509.14912v2
• Date: Thu, 06 Nov 2025 07:21:38 GMT
• Title: Back to Ear: Perceptually Driven High Fidelity Music Reconstruction
• Abstract summary: epsilonar-VAE is an open-source music signal reconstruction model that rethinks and optimize the Variational Autoencoders (VAEs)<n> Experiments show epsilonar-VAE at 44.1kHz substantially outperforms leading open-source models across diverse metrics.
• Score: 4.380428073231143
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Variational Autoencoders (VAEs) are essential for large-scale audio tasks like diffusion-based generation. However, existing open-source models often neglect auditory perceptual aspects during training, leading to weaknesses in phase accuracy and stereophonic spatial representation. To address these challenges, we propose {\epsilon}ar-VAE, an open-source music signal reconstruction model that rethinks and optimizes the VAE training paradigm. Our contributions are threefold: (i) A K-weighting perceptual filter applied prior to loss calculation to align the objective with auditory perception. (ii) Two novel phase losses: a Correlation Loss for stereo coherence, and a Phase Loss using its derivatives--Instantaneous Frequency and Group Delay--for precision. (iii) A new spectral supervision paradigm where magnitude is supervised by all four Mid/Side/Left/Right components, while phase is supervised only by the LR components. Experiments show {\epsilon}ar-VAE at 44.1kHz substantially outperforms leading open-source models across diverse metrics, showing particular strength in reconstructing high-frequency harmonics and the spatial characteristics.

Related papers

• Survey of Novel Deep Learning Architectures for Denoising Gravitational-wave Signals [0.0]
  We present the first controlled comparison of five neural-network architectures for gravitational-wave denoising.<n>We train identically across the full astrophysically-motivated spinning binary-black-hole parameter space.<n>A unifying principle emerges: matching network structure to the spectral anatomy of a coalescence outperforms brute-force model scaling.
  arXiv  Detail & Related papers  (2026-09-07T18:00:10Z)
• Understanding and Correcting Low-Frequency Bias in EEG Foundation Model [12.910215709640033]
  We identify a persistent low-frequency bias in representations learned by diverse EEG foundation models.<n>Our analysis links this bias to the interaction between EEG's $1/f$-like spectral structure and neural networks' tendency to preferentially learn low-frequency components.<n>We introduce FAME, a frequency-balanced masked autoencoding framework that reconstructs time--frequency activity in predefined EEG bands from masked EEG inputs.
  arXiv  Detail & Related papers  (2026-08-03T08:36:10Z)
• From Spatial to Spectral: An Efficient, Frequency-Guided Feature Representation Learner for Small Object Detection [5.01964718362187]
  Small object detection is bottlenecked by inherent feature scarcity of tiny targets.<n>We propose a paradigm textbfshift from spatial to spectral feature processing.<n>Our proposed textbfDERNet series outperforms YOLOv11 models under the same scale.
  arXiv  Detail & Related papers  (2026-06-22T18:09:49Z)
• Dynamic Spectral Denoising with Global-Context Attention for Multi-Behavior Recommendation [58.33732779555114]
  We argue that the key bottleneck is a representation-level failure caused by two coupled heterogeneities.<n>We propose Dynamic Spectral Denoising with Global-Context Attention for Multi-Behavior Recommendation (SpectraMB)<n>SpectraMB achieves the best results in most evaluation settings and exhibits improved robustness under noisy interactions.
  arXiv  Detail & Related papers  (2026-06-01T15:58:13Z)
• Learning to Refine: Spectral-Decoupled Iterative Refinement Framework for Precipitation Nowcasting [21.300422393514804]
  We propose a deterministic framework that reformulates nowcasting as progressive frequency-decoupled refinement.<n>SDIR first extracts a stable low-frequency synoptic skeleton, then iteratively refines high-frequency textures under physical constraints.<n> Experiments on three benchmarks show SDIR significantly outperforms SOTA methods in spatial accuracy.
  arXiv  Detail & Related papers  (2026-06-01T07:34:30Z)
• V-Co: A Closer Look at Visual Representation Alignment via Co-Denoising [65.5867130156805]
  We present V-Co, a systematic study of visual co-denoising in a unified JiT-based framework.<n>Our study reveals four key ingredients for effective visual co-denoising.<n>V-Co outperforms the underlying pixel-space diffusion baseline and strong prior pixel-diffusion methods.
  arXiv  Detail & Related papers  (2026-03-17T17:01:54Z)
• Flexible Gravitational-Wave Parameter Estimation with Transformers [73.44614054040267]
  We introduce a flexible transformer-based architecture paired with a training strategy that enables adaptation to diverse analysis settings at inference time.<n>We demonstrate that a single flexible model -- called Dingo-T1 -- can analyze 48 gravitational-wave events from the third LIGO-Virgo-KAGRA Observing Run.
  arXiv  Detail & Related papers  (2025-12-02T17:49:08Z)
• Toward Diffusible High-Dimensional Latent Spaces: A Frequency Perspective [73.86108756585857]
  We analyze encoder/decoder behaviors and find that decoders depend strongly on high-frequency latent components to recover details.<n>We introduce FreqWarm, a plug-and-play frequency warm-up curriculum that increases early-stage exposure to high-frequency latent signals.
  arXiv  Detail & Related papers  (2025-11-27T09:20:36Z)
• SONAR: Spectral-Contrastive Audio Residuals for Generalizable Deepfake Detection [6.042897432654865]
  Spectral-cONtrastive Audio Residuals (AR) is a frequency-guided framework for deepfake audio detectors.<n>AR disentangles an audio signal into complementary representations.<n> evaluated on the ASVspoof 2021 and in-the-wild benchmarks.
  arXiv  Detail & Related papers  (2025-11-26T12:16:38Z)
• SWAN: Self-supervised Wavelet Neural Network for Hyperspectral Image Unmixing [0.2624902795082451]
  We present SWAN: a three-stage, self-supervised wavelet neural network for estimation of endmembers and abundances from hyperspectral imagery.<n>The idea is to exploit latent symmetries from thus obtained invariant and covariant features using a self-supervised learning paradigm.<n> Experiments are conducted on two benchmark synthetic data sets with different signal-to-noise ratios as well as on three real benchmark hyperspectral data sets.
  arXiv  Detail & Related papers  (2025-10-26T10:05:48Z)
• prNet: Data-Driven Phase Retrieval via Stochastic Refinement [0.0]
  We propose a novel framework for phase retrieval that leverages Langevin dynamics to enable efficient posterior sampling.<n>Our method navigates the perception-distortion tradeoff through a combination of sampling, learned denoising, and model-based updates.
  arXiv  Detail & Related papers  (2025-07-13T12:25:06Z)
• SpINRv2: Implicit Neural Representation for Passband FMCW Radars [0.15193212081459279]
  We present SpINRv2, a neural framework for high-fidelity volumetric reconstruction using Frequency-Modulated Continuous-Wave radar.<n>Our core contribution is a fully differentiable frequency-domain forward model that captures the complex radar response using closed-form synthesis.<n>We introduce sparsity and regularization to disambiguate sub-bin ambiguities that arise at fine range resolutions.
  arXiv  Detail & Related papers  (2025-06-09T19:21:27Z)
• Blind Estimation of Sub-band Acoustic Parameters from Ambisonics Recordings using Spectro-Spatial Covariance Features [10.480691005356967]
  We propose a unified framework that blindly estimates reverberation time (T60), direct-to-reverberant ratio (DRR) and clarity (C50) across 10 frequency bands.<n>The proposed framework utilizes a novel feature named Spectro-Spatial Co Vector (SSCV), efficiently representing temporal, spectral as well as spatial information of the FOA signal.
  arXiv  Detail & Related papers  (2024-11-05T15:20:23Z)
• Mutual Learning for Acoustic Matching and Dereverberation via Visual Scene-driven Diffusion [93.32354378820648]
  We introduce MVSD, a mutual learning framework based on diffusion models. MVSD considers the two tasks symmetrically, exploiting the reciprocal relationship to facilitate learning from inverse tasks. Our framework can improve the performance of the reverberator and dereverberator.
  arXiv  Detail & Related papers  (2024-07-15T00:47:56Z)
• DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly Detection [80.20339155618612]
  DiffusionAD is a novel anomaly detection pipeline comprising a reconstruction sub-network and a segmentation sub-network.<n>A rapid one-step denoising paradigm achieves hundreds of times acceleration while preserving comparable reconstruction quality.<n>Considering the diversity in the manifestation of anomalies, we propose a norm-guided paradigm to integrate the benefits of multiple noise scales.
  arXiv  Detail & Related papers  (2023-03-15T16:14:06Z)
• High Fidelity Neural Audio Compression [92.4812002532009]
  We introduce a state-of-the-art real-time, high-fidelity, audio leveraging neural networks. It consists in a streaming encoder-decoder architecture with quantized latent space trained in an end-to-end fashion. We simplify and speed-up the training by using a single multiscale spectrogram adversary.
  arXiv  Detail & Related papers  (2022-10-24T17:52:02Z)
• FAMLP: A Frequency-Aware MLP-Like Architecture For Domain Generalization [73.41395947275473]
  We propose a novel frequency-aware architecture, in which the domain-specific features are filtered out in the transformed frequency domain. Experiments on three benchmarks demonstrate significant performance, outperforming the state-of-the-art methods by a margin of 3%, 4% and 9%, respectively.
  arXiv  Detail & Related papers  (2022-03-24T07:26:29Z)
• Conditioning Trick for Training Stable GANs [70.15099665710336]
  We propose a conditioning trick, called difference departure from normality, applied on the generator network in response to instability issues during GAN training. We force the generator to get closer to the departure from normality function of real samples computed in the spectral domain of Schur decomposition.
  arXiv  Detail & Related papers  (2020-10-12T16:50:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.