相关论文: Differentiable Time-Frequency Scattering on GPU

A target recognition framework relying on near-field integrated sensing and communication (ISAC) systems is proposed. By exploiting the distance-dependent spatial signatures provided by the near-field spherical wavefront, high-accuracy…

Diffusion probabilistic models have been recently used in a variety of tasks, including speech enhancement and synthesis. As a generative approach, diffusion models have been shown to be especially suitable for imputation problems, where…

Head-Related Transfer Functions (HRTFs) have fundamental applications for realistic rendering in immersive audio scenarios. However, they are strongly subject-dependent as they vary considerably depending on the shape of the ears, head and…

Early detection of factory machinery malfunctions is crucial in industrial applications. In machine anomalous sound detection (ASD), different machines exhibit unique vibration-frequency ranges based on their physical properties. Meanwhile,…

We propose the use of automatic differentiation through the programming framework jax for accelerating a variety of analysis tasks throughout gravitational wave (GW) science. Firstly, we demonstrate that complete waveforms which cover the…

This article introduces a new parametric synthesis method for sound textures based on existing works in visual and sound texture synthesis. Starting from a base sound signal, an optimization process is performed until the cross-correlations…

Diffusion models can learn rich representations during data generation, showing potential for Self-Supervised Learning (SSL), but they face a trade-off between generative quality and discriminative performance. Their iterative sampling also…

We present a transformer-based speech-declipping model that effectively recovers clipped signals across a wide range of input signal-to-distortion ratios (SDRs). While recent time-domain deep neural network (DNN)-based declippers have…

The estimation of glottal flow from a speech waveform is a key method for speech analysis and parameterization. Significant research effort has been made to dissociate the first vocal tract resonance from the glottal formant (the…

A Python package for the calculation of spectrograms with optimized time and frequency resolution for application in the analysis of numerical simulations on ultrashort pulse propagation is presented. Gabor's uncertainty principle prevents…

Context propagation remains a central challenge in language model architectures, particularly in tasks requiring the retention of long-range dependencies. Conventional attention mechanisms, while effective in many applications, exhibit…

In this paper, we propose a new convolutional layer called Depthwise-STFT Separable layer that can serve as an alternative to the standard depthwise separable convolutional layer. The construction of the proposed layer is inspired by the…

Motivated by the need for analysing large spatio-temporal panel data, we introduce a novel dimensionality reduction methodology for $n$-dimensional random fields observed across a number $S$ spatial locations and $T$ time periods. We call…

Time-frequency representations (TFRs) of signals, such as the windowed Fourier transform (WFT), wavelet transform (WT) and their synchrosqueezed variants (SWFT, SWT), provide powerful analysis tools. However, there are many important issues…

Score-based generative models (SGMs) have recently shown impressive results for difficult generative tasks such as the unconditional and conditional generation of natural images and audio signals. In this work, we extend these models to the…

Personalized federated learning algorithms have shown promising results in adapting models to various distribution shifts. However, most of these methods require labeled data on testing clients for personalization, which is usually…

As a promising distributed machine learning paradigm that enables collaborative training without compromising data privacy, Federated Learning (FL) has been increasingly used in AIoT (Artificial Intelligence of Things) design. However, due…

Joint phase-time arrays (JPTA) is a new mmWave radio frequency front-end architecture constructed with appending time-delay elements to phase shifters for analog beamforming. JPTA allows the mmWave base station (BS) to form multiple…

Neuromorphic computing offers an energy-efficient alternative to conventional deep learning accelerators for real-time time-series processing. However, many edge applications, such as wireless sensing and audio recognition, generate…

Typical high quality text-to-speech (TTS) systems today use a two-stage architecture, with a spectrum model stage that generates spectral frames and a vocoder stage that generates the actual audio. High-quality spectrum models usually…