18 accepted papers
In multimodal learning, CLIP has been recognized as the \textit{de facto} method for learning a shared latent space across multiple modalities, placing similar representations close to each other and moving them away from dissimilar ones. Although CLIP-based losses effectively align modalities at th…
High-resolution image synthesis remains a core challenge in generative modeling, particularly in balancing computational efficiency with the preservation of fine-grained visual detail. We present $\textit{Latent Wavelet Diffusion (LWD)}$, a lightweight training framework that significantly improves…
Video-to-audio (V2A) generation aims to synthesize realistic and semantically aligned audio from silent videos, with potential applications in video editing, Foley sound design, and assistive multimedia. Although the excellent results, existing approaches either require costly joint training on larg…
Multimodal learning plays a pivotal role in advancing artificial intelligence systems by incorporating information from multiple modalities to build a more comprehensive representation. Despite its importance, current state-of-the-art models still suffer from severe limitations that prevent the succ…
Human perception integrates multiple modalities—such as vision, hearing, and language—into a unified understanding of the surrounding reality. While recent multimodal models have achieved significant progress by aligning pairs of modalities via contrastive learning, their solutions are unsuitable wh…
Generating images from brain waves is gaining increasing attention due to its potential to advance brain-computer interface (BCI) systems by understanding how brain signals encode visual cues. Most of the literature has focused on fMRI-to-Image tasks as fMRI is characterized by high spatial resoluti…
Directly sending audio signals from a transmitter to a receiver across a noisy channel may absorb consistent bandwidth and be prone to errors when trying to recover the transmitted bits. On the contrary, the recent semantic communication approach proposes to send the semantics and then regenerate se…
Functional link adaptive filters (FLAFs) utilize expansion blocks to nonlinearly augment the input signal to a higher dimensional space, after which an adaptive weight algorithm is applied. These filters are useful for nonlinear system identification tasks, as they can update a large number of coeff…
Semantic communication is poised to play a pivotal role in shaping the landscape of future AI-driven communication systems. Its challenge of extracting semantic information from the original complex content and regenerating semantically consistent data at the receiver, possibly being robust to chann…
Sound design involves creatively selecting, recording, and editing sound effects for various media like cinema, video games, and virtual/augmented reality. One of the most time-consuming steps when designing sound is synchronizing audio with video. In some cases, environmental recordings from video…
The primary goal of the L3DAS23 Signal Processing Grand Challenge at ICASSP 2023 is to promote and support collaborative research on machine learning for 3D audio signal processing, with a specific emphasis on 3D speech enhancement and 3D Sound Event Localization and Detection in Extended Reality ap…
The L3DAS22 Challenge is aimed at encouraging the development of machine learning strategies for 3D speech enhancement and 3D sound localization and detection in office-like environments. This challenge improves and extends the tasks of the L3DAS21 edition <sup xmlns:mml="http://www.w3.org/1998/Math…
Deep probabilistic generative models have achieved incredible success in many fields of application. Among such models, variational autoencoders (VAEs) have proved their ability in modeling a generative process by learning a latent representation of the input. In this paper, we propose a novel VAE d…
In this paper, we consider the design of deep neural networks augmented with multiple auxiliary classifiers departing from the main (backbone) network. These classifiers can be used to perform early-exit from the network at various layers, making them convenient for energy-constrained applications s…
Frequency-domain adaptive filters (FDAFs) have been widely used over the years, but they are still matter of research due to their powerful capabilities that differentiate them from the whole family of time-domain adaptive filters. This paper aims at providing an overview on FDAFs through a unifying…
Learning from data in the quaternion domain enables us to exploit internal dependencies of 4D signals and treating them as a single entity. One of the models that perfectly suits with quaternion-valued data processing is represented by 3D acoustic signals in their spherical harmonics decomposition.…
Complex-valued neural networks (CVNNs) have been shown to be powerful nonlinear approximators when the input data can be properly modeled in the complex domain. One of the major challenges in scaling up CVNNs in practice is the design of complex activation functions. Recently, we proposed a novel fr…
The paper introduces a novel class of complex nonlinear filters, the complex functional link polynomial (CFLiP) filters. These filters present many interesting properties. They are a sub-class of linear-in-the-parameter nonlinear filters. They satisfy all the conditions of Stone-Weirstrass theorem a…