Latent Fourier Transform

• URL: http://arxiv.org/abs/2604.17986v1
• Date: Mon, 20 Apr 2026 09:08:13 GMT
• Title: Latent Fourier Transform
• Abstract summary: LatentFT is a framework that provides novel frequency-domain controls for generative music models.<n>By masking latents in the frequency domain during training, our method yields representations that can be manipulated coherently at inference.<n>Experiments and listening tests show that LatentFT improves condition adherence and quality compared to baselines.
• Score: 1.6781763863175045
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We introduce the Latent Fourier Transform (LatentFT), a framework that provides novel frequency-domain controls for generative music models. LatentFT combines a diffusion autoencoder with a latent-space Fourier transform to separate musical patterns by timescale. By masking latents in the frequency domain during training, our method yields representations that can be manipulated coherently at inference. This allows us to generate musical variations and blends from reference examples while preserving characteristics at desired timescales, which are specified as frequencies in the latent space. LatentFT parallels the role of the equalizer in music production: while traditional equalizers operates on audible frequencies to shape timbre, LatentFT operates on latent-space frequencies to shape musical structure. Experiments and listening tests show that LatentFT improves condition adherence and quality compared to baselines. We also present a technique for hearing frequencies in the latent space in isolation, and show different musical attributes reside in different regions of the latent spectrum. Our results show how frequency-domain control in latent space provides an intuitive, continuous frequency axis for conditioning and blending, advancing us toward more interpretable and interactive generative music models.

Related papers

• WaveletDiff: Multilevel Wavelet Diffusion For Time Series Generation [15.28917997999402]
  WaveletDiff is a novel framework that trains diffusion models directly on wavelet coefficients to exploit the inherent multi-resolution structure of time series data.<n>It consistently outperforms state-of-the-art time-domain and frequency-domain generative methods on both short and long time series across five diverse performance metrics.
  arXiv  Detail & Related papers  (2025-10-13T18:47:33Z)
• Fourier Basis Mapping: A Time-Frequency Learning Framework for Time Series Forecasting [25.304812011127257]
  We introduce a novel method for integrating time-frequency features through Fourier basis expansion and mapping in the time-frequency space.<n>Our approach extracts explicit frequency features while preserving temporal characteristics.<n>The results are validated on diverse real-world datasets for both long-term and short-term forecasting tasks.
  arXiv  Detail & Related papers  (2025-07-13T01:45:27Z)
• LSCD: Lomb-Scargle Conditioned Diffusion for Time series Imputation [55.800319453296886]
  Time series with missing or irregularly sampled data are a persistent challenge in machine learning.<n>We introduce a different Lombiable--Scargle layer that enables a reliable computation of the power spectrum of irregularly sampled data.
  arXiv  Detail & Related papers  (2025-06-20T14:48:42Z)
• Freqformer: Image-Demoiréing Transformer via Efficient Frequency Decomposition [83.40450475728792]
  We present Freqformer, a Transformer-based framework specifically designed for image demoir'eing through targeted frequency separation.<n>Our method performs an effective frequency decomposition that explicitly splits moir'e patterns into high-frequency spatially-localized textures and low-frequency scale-robust color distortions.<n>Experiments on various demoir'eing benchmarks demonstrate that Freqformer achieves state-of-the-art performance with a compact model size.
  arXiv  Detail & Related papers  (2025-05-25T12:23:10Z)
• Neural Fourier Modelling: A Highly Compact Approach to Time-Series Analysis [9.969451740838418]
  We introduce Neural Fourier Modelling (NFM), a compact yet powerful solution for time-series analysis. NFM is grounded in two key properties of the Fourier transform (FT): (i) the ability to model finite-length time series as functions in the Fourier domain, and (ii) the capacity for data manipulation within the Fourier domain. NFM achieves state-of-the-art performance on a wide range of tasks, including challenging time-series scenarios with previously unseen sampling rates at test time.
  arXiv  Detail & Related papers  (2024-10-07T02:39:55Z)
• F2former: When Fractional Fourier Meets Deep Wiener Deconvolution and Selective Frequency Transformer for Image Deblurring [8.296475046681696]
  We propose a novel approach based on the Fractional Fourier Transform (FRFT), a unified spatial-frequency representation. We show that the performance of our proposed method is superior to other state-of-the-art (SOTA) approaches.
  arXiv  Detail & Related papers  (2024-09-03T17:05:12Z)
• FourierMamba: Fourier Learning Integration with State Space Models for Image Deraining [71.46369218331215]
  Image deraining aims to remove rain streaks from rainy images and restore clear backgrounds. We propose a new framework termed FourierMamba, which performs image deraining with Mamba in the Fourier space.
  arXiv  Detail & Related papers  (2024-05-29T18:58:59Z)
• Frequency-Aware Deepfake Detection: Improving Generalizability through Frequency Space Learning [81.98675881423131]
  This research addresses the challenge of developing a universal deepfake detector that can effectively identify unseen deepfake images. Existing frequency-based paradigms have relied on frequency-level artifacts introduced during the up-sampling in GAN pipelines to detect forgeries. We introduce a novel frequency-aware approach called FreqNet, centered around frequency domain learning, specifically designed to enhance the generalizability of deepfake detectors.
  arXiv  Detail & Related papers  (2024-03-12T01:28:00Z)
• Dynamic Temporal Filtering in Video Models [128.02725199486719]
  We present a new recipe of temporal feature learning, namely Dynamic Temporal Filter (DTF) DTF learns a specialized frequency filter for every spatial location to model its long-range temporal dynamics. It is feasible to plug DTF block into ConvNets and Transformer, yielding DTF-Net and DTF-Transformer.
  arXiv  Detail & Related papers  (2022-11-15T15:59:28Z)
• Transforming Spectrum and Prosody for Emotional Voice Conversion with Non-Parallel Training Data [91.92456020841438]
  Many studies require parallel speech data between different emotional patterns, which is not practical in real life. We propose a CycleGAN network to find an optimal pseudo pair from non-parallel training data. We also study the use of continuous wavelet transform (CWT) to decompose F0 into ten temporal scales, that describes speech prosody at different time resolution.
  arXiv  Detail & Related papers  (2020-02-01T12:36:55Z)

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.