English
Related papers

Related papers: Differentiable Time-Frequency Scattering on GPU

200 papers

High-resolution time-frequency (TF) analysis plays crucial role in characterizing multicomponent signal (MCSs) and estimating oscillatory properties. Linear time-frequency representations (TFRs) such as classical short-time Fourier…

Signal Processing · Electrical Eng. & Systems 2023-12-12 Rayyan Abdalla

In this paper, 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 by making these parameters continuous. Our approach…

Signal Processing · Electrical Eng. & Systems 2023-08-07 Maxime Leiber , Yosra Marnissi , Axel Barrau , Mohammed El Badaoui

We introduce an audio texture synthesis algorithm based on scattering moments. A scattering transform is computed by iteratively decomposing a signal with complex wavelet filter banks and computing their amplitude envelop. Scattering…

Applications · Statistics 2013-11-05 Joan Bruna , Stéphane Mallat

The head-related transfer function (HRTF) characterizes the frequency response of the sound traveling path between a specific location and the ear. When it comes to estimating HRTFs by neural network models, angle-specific models greatly…

Signal Processing · Electrical Eng. & Systems 2025-05-06 Keng-Wei Chang , Yih-Liang Shen , Tai-Shi Chi

This paper explores the innovative application of the Fractional Fourier Transform (FrFT) in sound synthesis, highlighting its potential to redefine time-frequency analysis in audio processing. As an extension of the classical Fourier…

Sound · Computer Science 2025-06-12 Esteban Gutiérrez , Rodrigo Cádiz , Carlos Sing Long , Frederic Font , Xavier Serra

Spiking Neural Networks (SNNs) demonstrate significant potential for energy-efficient neuromorphic computing through an event-driven paradigm. While training methods and computational models have greatly advanced, SNNs struggle to achieve…

Neural and Evolutionary Computing · Computer Science 2025-10-27 Jieyuan Zhang , Xiaolong Zhou , Shuai Wang , Wenjie Wei , Hanwen Liu , Qian Sun , Malu Zhang , Yang Yang , Haizhou Li

Instrumental playing techniques such as vibratos, glissandos, and trills often denote musical expressivity, both in classical and folk contexts. However, most existing approaches to music similarity retrieval fail to describe timbre beyond…

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…

Sound · Computer Science 2026-04-21 Mason Wang , Cheng-Zhi Anna Huang

This paper introduces a multi-microphone method for extracting a desired speaker from a mixture involving multiple speakers and directional noise in a reverberant environment. In this work, we propose leveraging the instantaneous relative…

Sound · Computer Science 2025-02-11 Aviad Eisenberg , Sharon Gannot , Shlomo E. Chazan

Robustness against temporal variations is important for emotion recognition from speech audio, since emotion is ex-pressed through complex spectral patterns that can exhibit significant local dilation and compression on the time axis…

Audio and Speech Processing · Electrical Eng. & Systems 2020-03-10 Eric Guizzo , Tillman Weyde , Jack Barnett Leveson

Very large time series are increasingly available from an ever wider range of IoT-enabled sensors deployed in different environments. Significant insights can be gained by mining temporal patterns from these time series. Unlike traditional…

Databases · Computer Science 2021-11-18 Van Long Ho , Nguyen Ho , Torben Bach Pedersen

Speech separation has been very successful with deep learning techniques. Substantial effort has been reported based on approaches over spectrogram, which is well known as the standard time-and-frequency cross-domain representation for…

Sound · Computer Science 2019-04-17 Gene-Ping Yang , Chao-I Tuan , Hung-Yi Lee , Lin-shan Lee

Fourier transforms are an often necessary component in many computational tasks, and can be computed efficiently through the fast Fourier transform (FFT) algorithm. However, many applications involve an underlying continuous signal, and a…

Mathematical Software · Computer Science 2022-09-27 Eric Bezzam , Sepand Kashani , Paul Hurley , Martin Vetterli , Matthieu Simeoni

In this paper we propose a scalable version of a state-of-the-art deterministic time-invariant feature extraction approach based on consecutive changes of basis and nonlinearities, namely, the scattering network. The first focus of the…

Machine Learning · Statistics 2017-07-20 Randall Balestriero , Herve Glotin

Many multi-microphone speech enhancement algorithms require the relative transfer function (RTF) vector of the desired speech source, relating the acoustic transfer functions of all array microphones to a reference microphone. In this…

Audio and Speech Processing · Electrical Eng. & Systems 2022-11-22 N. Gößling , S. Doclo

The fundamental concepts and challenges of orthogonal time frequency space (OTFS) modulation have been reviewed in Part I of this three-part tutorial. In this second part, we provide an overview of the state-of-the-art transceiver designs…

Information Theory · Computer Science 2022-09-13 Shuangyang Li , Weijie Yuan , Zhiqiang Wei , Robert Schober , Giuseppe Caire

From a machine learning perspective, the human ability localize sounds can be modeled as a non-parametric and non-linear regression problem between binaural spectral features of sound received at the ears (input) and their sound-source…

Sound · Computer Science 2015-02-12 Yuancheng Luo , Dmitry N. Zotkin , Ramani Duraiswami

Sound event detection (SED) has significantly benefited from self-supervised learning (SSL) approaches, particularly masked audio transformer for SED (MAT-SED), which leverages masked block prediction to reconstruct missing audio segments.…

Audio and Speech Processing · Electrical Eng. & Systems 2025-03-03 Hyeonuk Nam , Yong-Hwa Park

The spiking neural networks (SNNs) that efficiently encode temporal sequences have shown great potential in extracting audio-visual joint feature representations. However, coupling SNNs (binary spike sequences) with transformers…

Multimedia · Computer Science 2024-07-12 Wenrui Li , Penghong Wang , Ruiqin Xiong , Xiaopeng Fan

Big time series are increasingly available from an ever wider range of IoT-enabled sensors deployed in various environments. Significant insights can be gained by mining temporal patterns from these time series. Temporal pattern mining…

Databases · Computer Science 2023-06-21 Van Long Ho , Nguyen Ho , Torben Bach Pedersen , Panagiotis Papapetrou