6 papers
Mitigating data replication in text-to-audio generative diffusion models through anti-memorization guidance
Francisco Messina, Francesca Ronchini, Luca Comanducci +2
A persistent challenge in generative audio models is data replication, where the model unintentionally generates parts of its training data during inference. In this work, we addre…
PAGURI: a user experience study of creative interaction with text-to-music models
Francesca Ronchini, Luca Comanducci, Gabriele Perego +1
In recent years, text-to-music models have been the biggest breakthrough in automatic music generation. While they are unquestionably a showcase of technological progress, it is no…
AI-Assisted Music Production: A User Study on Text-to-Music Models
Francesca Ronchini, Luca Comanducci, Simone Marcucci +1
Text-to-music models have revolutionized the creative landscape, offering new possibilities for music creation. Yet their integration into musicians workflows remains underexplored…
Diffused Responsibility: Analyzing the Energy Consumption of Generative Text-to-Audio Diffusion Models
Riccardo Passoni, Francesca Ronchini, Luca Comanducci +2
Text-to-audio models have recently emerged as a powerful technology for generating sound from textual descriptions. However, their high computational demands raise concerns about e…
MambaFoley: Foley Sound Generation using Selective State-Space Models
Marco Furio Colombo, Francesca Ronchini, Luca Comanducci +1
Recent advancements in deep learning have led to widespread use of techniques for audio content generation, notably employing Denoising Diffusion Probabilistic Models (DDPM) across…
Towards HRTF Personalization using Denoising Diffusion Models
Juan Camilo AlbarracÃn Sánchez, Luca Comanducci, Mirco Pezzoli +1
Head-Related Transfer Functions (HRTFs) have fundamental applications for realistic rendering in immersive audio scenarios. However, they are strongly subject-dependent as they var…