C. Marinoni
YOU?
Author Swipe
FoleyGRAM: Video-to-Audio Generation with GRAM-Aligned Multimodal Encoders Open
In this work, we present FoleyGRAM, a novel approach to video-to-audio generation that emphasizes semantic conditioning through the use of aligned multimodal encoders. Building on prior advancements in video-to-audio generation, FoleyGRAM …
Controllable Audio-Visual Viewpoint Generation from 360° Spatial Information Open
The generation of sounding videos has seen significant advancements with the advent of diffusion models. However, existing methods often lack the fine-grained control needed to generate viewpoint-specific content from larger, immersive 360…
StereoSync: Spatially-Aware Stereo Audio Generation from Video Open
Although audio generation has been widely studied over recent years, video-aligned audio generation still remains a relatively unexplored frontier. To address this gap, we introduce StereoSync, a novel and efficient model designed to gener…
View article: FolAI: Synchronized Foley Sound Generation with Semantic and Temporal Alignment
FolAI: Synchronized Foley Sound Generation with Semantic and Temporal Alignment Open
Traditional sound design workflows rely on manual alignment of audio events to visual cues, as in Foley sound design, where everyday actions like footsteps or object interactions are recreated to match the on-screen motion. This process is…
Overview of the L3DAS23 Challenge on Audio-Visual Extended Reality Open
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 …
Cosmography of the Local Universe by Multipole Analysis of the Expansion Rate Fluctuation Field Open
We establish a relationship between the multipoles of the expansion rate fluctuation field $η,$ which capture in an accurate way deviations from isotropy in the redshift-distance relation, and the multipoles of the covariant cosmographic p…
L3DAS23: Learning 3D Audio Sources for Audio-Visual Extended Reality Open
The primary goal of the L3DAS (Learning 3D Audio Sources) project is to stimulate and support collaborative research studies concerning machine learning techniques applied to 3D audio signal processing. To this end, the L3DAS23 Challenge, …
Covariant cosmography: the observer-dependence of the Hubble parameter Open
The disagreement between low- and high-redshift measurements of the Hubble parameter is emerging as a serious challenge to the standard model of cosmology. We develop a covariant cosmographic analysis of the Hubble parameter in a general s…
The multipolar structure of the local expansion rate Open
We design a new observable, the $\eta$ expansion rate fluctuation, to characterize deviations from linearity in the redshift-distance relationship in the local Universe. We also show how to compress the resulting signal into spherical harm…
Diffusion models for audio semantic communication Open
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 a…
The multipole expansion of the local expansion rate Open
We design a new observable, the expansion rate fluctuation $η$, to characterize deviations from the linear relation between redshift and distance in the local universe. We also show how to compress the resulting signal into spherical harmo…
Constraining spatial curvature with large-scale structure Open
We analyse the clustering of matter on large scales in an extension of the concordance model that allows for spatial curvature. We develop a consistent approach to curvature and wide-angle effects on the galaxy 2-point correlation function…
L3DAS22 Challenge: Learning 3D Audio Sources in a Real Office Environment Open
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 th…
L3DAS22 Challenge: Learning 3D Audio Sources in a Real Office Environment Open
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 th…
L3DAS21 Challenge: Machine Learning for 3D Audio Signal Processing Open
The L3DAS21 Challenge is aimed at encouraging and fostering collaborative research on machine learning for 3D audio signal processing, with particular focus on 3D speech enhancement (SE) and 3D sound localization and detection (SELD). Alon…
Redshift drift in radially inhomogeneous Lemaître-Tolman-Bondi spacetimes Open
We provide a formula for estimating the redshift and its secular change (redshift drift) in Lemaître-Tolman-Bondi (LTB) spherically symmetric universes. We compute the scaling of the redshift drift for LTB models that predict Hubble diagra…
L3DAS21 challenge: machine learning for 3D audio signal processing Open
The L3DAS21 Challenge11www.13das.com/mlsp2021 is aimed at encouraging and fostering collaborative research on machine learning for 3D audio signal processing, with particular focus on 3D speech enhancement (SE) and 3D sound localization an…
Proposal for a Real-Time Detection of our Acceleration through Space Open
Our proper acceleration with respect to the cosmic microwave background results in a real-time change of the angular position of distant extragalactic sources. The cosmological component of this aberration drift signal, the noninertial mot…
E pur si muove! Proposal for a real-time detection of our acceleration through space Open
Our proper acceleration with respect to the Cosmic Microwave Background results in a real-time change of the angular position of distant extragalactic sources. The cosmological component of this aberration drift signal, the non-inertial mo…
The VIMOS Public Extragalactic Redshift Survey (VIPERS) Open
We present the full public data release (PDR-2) of the VIMOS Public Extragalactic Redshift Survey (VIPERS), performed at the ESO VLT. We release redshifts, spectra, CFHTLS magnitudes and ancillary information (as masks and weights) for a c…
Diagnostic of Horndeski theories Open
We study the effects of Horndeski models of dark energy on the observables of\nthe large-scale structure in the late time universe. A novel classification\ninto {\\it Late dark energy}, {\\it Early dark energy} and {\\it Early modified\ngr…
View article: The VIMOS Public Extragalactic Redshift Survey (VIPERS). Full spectroscopic data and auxiliary information release (PDR-2)
The VIMOS Public Extragalactic Redshift Survey (VIPERS). Full spectroscopic data and auxiliary information release (PDR-2) Open
We present the full public data release (PDR-2) of the VIMOS Public Extragalactic Redshift Survey (VIPERS), performed at the ESO VLT. We release redshifts, spectra, CFHTLS magnitudes and ancillary information (as masks and weights) for a c…