Differentiable adaptive short-time Fourier transform with respect to the window length

• URL: http://arxiv.org/abs/2308.02418v1
• Date: Wed, 26 Jul 2023 06:55:42 GMT
• Title: Differentiable adaptive short-time Fourier transform with respect to the window length
• Authors: Maxime Leiber, Yosra Marnissi, Axel Barrau, Mohammed El Badaoui
• Abstract summary: This paper presents a gradient-based method for on-the-fly optimization for both per-frame and per-frequency window length of the short-time Fourier transform (STFT) The resulting differentiable adaptive STFT possesses commendable properties, such as the ability to adapt in the same time-frequency representation to both transient and stationary components, while being easily optimized by gradient descent.
• Score: 4.664495510551647
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: This paper presents a gradient-based method for on-the-fly optimization for both per-frame and per-frequency window length of the short-time Fourier transform (STFT), related to previous work in which we developed a differentiable version of STFT by making the window length a continuous parameter. The resulting differentiable adaptive STFT possesses commendable properties, such as the ability to adapt in the same time-frequency representation to both transient and stationary components, while being easily optimized by gradient descent. We validate the performance of our method in vibration analysis.

Related papers

• Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform [11.05158127763157]
  We propose a differentiable formulation of the STFT that enables gradient-based optimization of its parameters.<n>Our approach integrates seamlessly with neural networks, allowing joint optimization of the STFT parameters and network weights.<n>The efficacy of the proposed differentiable STFT in enhancing TFRs and improving performance in downstream tasks is demonstrated.
  arXiv  Detail & Related papers  (2025-06-26T16:24:27Z)
• Beyond Homogeneous Attention: Memory-Efficient LLMs via Fourier-Approximated KV Cache [67.47789629197857]
  We propose a training-free framework that exploits the heterogeneous roles of transformer head dimensions.<n>By projecting the long-context-insensitive dimensions onto Fourier bases, FourierAttention approximates their temporal evolution with fixed-length spectral coefficients.<n>We show that FourierAttention achieves the best long-context accuracy on LongBench and Needle-In-A-Haystack.
  arXiv  Detail & Related papers  (2025-06-13T15:35:54Z)
• State-Free Inference of State-Space Models: The Transfer Function Approach [132.83348321603205]
  State-free inference does not incur any significant memory or computational cost with an increase in state size. We achieve this using properties of the proposed frequency domain transfer function parametrization. We report improved perplexity in language modeling over a long convolutional Hyena baseline.
  arXiv  Detail & Related papers  (2024-05-10T00:06:02Z)
• Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation [67.13876021157887]
  Dynamic Tuning (DyT) is a novel approach to improve both parameter and inference efficiency for ViT adaptation. DyT achieves superior performance compared to existing PEFT methods while evoking only 71% of their FLOPs on the VTAB-1K benchmark.
  arXiv  Detail & Related papers  (2024-03-18T14:05:52Z)
• Differentiable short-time Fourier transform with respect to the hop length [4.664495510551647]
  We propose a differentiable version of the short-time Fourier transform (STFT) that allows for gradient-based optimization of the hop length or the frame temporal position. Our approach provides improved control over the temporal positioning of frames, as the continuous nature of the hop length allows for a more finely-tuned optimization.
  arXiv  Detail & Related papers  (2023-07-26T07:04:09Z)
• Experimental implementation of the optical fractional Fourier transform in the time-frequency domain [0.0]
  We present the experimental realization of the fractional Fourier transform in the time-frequency domain using an atomic quantum-optical memory system. We have verified the FrFT by analyses of chroncyclic Wigner functions measured via a shot-noise limited homodyne detector.
  arXiv  Detail & Related papers  (2023-03-23T14:39:52Z)
• Transform Once: Efficient Operator Learning in Frequency Domain [69.74509540521397]
  We study deep neural networks designed to harness the structure in frequency domain for efficient learning of long-range correlations in space or time. This work introduces a blueprint for frequency domain learning through a single transform: transform once (T1)
  arXiv  Detail & Related papers  (2022-11-26T01:56:05Z)
• Lightweight and High-Fidelity End-to-End Text-to-Speech with Multi-Band Generation and Inverse Short-Time Fourier Transform [9.606821628015933]
  We propose a lightweight end-to-end text-to-speech model using multi-band generation and inverse short-time Fourier transform. Experimental results show that our model synthesized speech as natural as that synthesized by VITS. A smaller version of the model significantly outperformed a lightweight baseline model with respect to both naturalness and inference speed.
  arXiv  Detail & Related papers  (2022-10-28T08:15:05Z)
• A differentiable short-time Fourier transform with respect to the window length [4.0527583944137255]
  We revisit the use of spectrograms in neural networks, by making the window length a continuous parameter optimizable by descent gradient. The contribution is mostly theoretical at this point, but plugging the modified STFT into any existing neural network is straightforward.
  arXiv  Detail & Related papers  (2022-08-23T11:38:33Z)
• Non-Convex Optimization with Certificates and Fast Rates Through Kernel Sums of Squares [68.8204255655161]
  We consider potentially non- optimized approximation problems. In this paper, we propose an algorithm that achieves close to optimal a priori computational guarantees.
  arXiv  Detail & Related papers  (2022-04-11T09:37:04Z)
• Stable, Fast and Accurate: Kernelized Attention with Relative Positional Encoding [63.539333383965726]
  We propose a novel way to accelerate attention calculation for Transformers with relative positional encoding (RPE) Based upon the observation that relative positional encoding forms a Toeplitz matrix, we mathematically show that kernelized attention with RPE can be calculated efficiently using Fast Fourier Transform (FFT)
  arXiv  Detail & Related papers  (2021-06-23T17:51:26Z)
• Optimizing Short-Time Fourier Transform Parameters via Gradient Descent [24.80575785857326]
  We show an approach that allows us to obtain a gradient for STFT parameters with respect to arbitrary cost functions. We do so for parameter values that stay constant throughout an input, but also for cases where these parameters have to dynamically change over time to accommodate varying signal characteristics.
  arXiv  Detail & Related papers  (2020-10-28T15:49:56Z)
• Stochastic Optimization with Heavy-Tailed Noise via Accelerated Gradient Clipping [69.9674326582747]
  We propose a new accelerated first-order method called clipped-SSTM for smooth convex optimization with heavy-tailed distributed noise in gradients. We prove new complexity that outperform state-of-the-art results in this case. We derive the first non-trivial high-probability complexity bounds for SGD with clipping without light-tails assumption on the noise.
  arXiv  Detail & Related papers  (2020-05-21T17:05:27Z)

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.