iiinova — where your digital self keeps evolving

Luca Comanducci @lucacomanducci.bsky.social · 20/05/2025

Glad to have been presented the FakeMusicCaps dataset and the risks and issues behind deepfake music detection! Link to the paper --> arxiv.org/pdf/2409.10684 Link to the dataset --> zenodo.org/records/1506... #AIMusic #GenerativeAI #Deepfake #AI #GenerativeMusic

031

Reposted by Luca Comanducci

arXiv eess.AS Audio and Speech Processing @eessas-bot.bsky.social · 13/05/2025

Riccardo Passoni, Francesca Ronchini, Luca Comanducci, Romain Serizel, Fabio Antonacci: Diffused Responsibility: Analyzing the Energy Consumption of Generative Text-to-Audio Diffusion Models arxiv.org/abs/2505.07615 arxiv.org/pdf/2505.07615 arxiv.org/html/2505.07615

146

Reposted by Luca Comanducci

arXiv Sound @arxiv-sound.bsky.social · 13/05/2025

Energy consumption of 7 text-to-audio diffusion models was analyzed, identifying the trade-off between audio quality and energy usage at inference time by finding Pareto-optimal solutions.

arxiv.org

Diffused Responsibility: Analyzing the Energy Consumption of Generative Text-to-Audio Diffusion Models

Riccardo Passoni, Francesca Ronchini, Luca Comanducci, Romain Serizel, Fabio Antonacci

001

Reposted by Luca Comanducci

arXiv Sound @arxiv-sound.bsky.social · 07/01/2025

DDPMs, conditioned on anthropometric measurements, generated personalized HRIRs, demonstrating feasibility for HRTF personalization and comparable performance to existing methods.

arxiv.org

Towards HRTF Personalization using Denoising Diffusion Models

Juan Camilo Albarracín Sánchez, Luca Comanducci, Mirco Pezzoli, Fabio Antonacci

021

Luca Comanducci @lucacomanducci.bsky.social · 21/12/2024

2 Papers accepted at #ICASSP25 🇮🇳 hope to see you in india! - MambaFoley: Foley Sound Generation using Selective State-Space Models (arxiv.org/pdf/2409.09162) - Towards HRTF Personalization using Denoising Diffusion Models (arxiv soon) #ICASSP25 #ICASSP #generativeai

arxiv.org

120

Reposted by Luca Comanducci

hugofloresgarcía @hugofloresgarcia.bsky.social · 12/12/2024

new paper! 🗣️Sketch2Sound💥 Sketch2Sound can create sounds from sonic imitations (i.e., a vocal imitation or a reference sound) via interpretable, time-varying control signals. paper: arxiv.org/abs/2412.08550 web: hugofloresgarcia.art/sketch2sound

2239

Reposted by Luca Comanducci

DCASE Challenge @dcase-challenge.bsky.social · 10/12/2024

The tasks for DCASE challenge 2025 have been announced. dcase.community/articles/cha... Stay tuned for more details.

dcase.community

Challenge tasks for DCASE2025 - DCASE

The DCASE Steering Group has reviewed the task proposals...

074