Recent developments in algorithmic fairness started to investigate the interaction between multiple sensitive information through an intersectional perspective. We introduce a new definition of intersectional fairness based on a multivariate extension of the Generalized Disparate Impact (GeDI). Our approach leverages a neural network to transform multiple protected groups into a univariate latent space that maximizes correlation with the target, effectively capturing unfairness across all potential subgroups even with limited data samples. Empirical evaluations on several benchmarks demonstrate that our method can be effectively used as a loss regularizer during neural network training, offering stronger performance guarantees compared to existing intersectional statistical parity definitions while also allowing to manage continuous inputs and targets.

We make two contributions in the field of AI fairness over continuous protected attributes. First, we show that the Hirschfeld-Gebelein-Renyi (HGR) indicator (the only one currently available for such a case) is valuable but subject to a few crucial limitations regarding semantics, interpretability, and robustness. Second, we introduce a family of indicators that are: 1) complementary to HGR in terms of semantics; 2) fully interpretable and transparent; 3) robust over finite samples; 4) configurable to suit specific applications. Our approach also allows us to define fine-grained constraints to permit certain types of dependence and forbid others selectively. By expanding the available options for continuous protected attributes, our approach represents a significant contribution to the area of fair artificial intelligence.

Recent developments in the field of deep learning have steered research on music generation systems towards a massive use of large end-to-end neural architectures. The capability of these systems to produce convincing outputs has been extensively proven. Nonetheless, they usually come with several drawbacks, such as a low degree of user control, a lack of global structure, and the inherent impossibility of online generation due to high computational costs. Our contribution is two-fold: first, we identify these limitations and show how they have been discussed and partially addressed in the existing literature; then, we propose a novel music generation approach aimed at overcoming such limitations, by properly combining a set of samples under user-defined constraints. We model our task as a job-shop problem, and we show that interesting results can be obtained at very low computational costs. Our framework is genre-independent as it deals with samples metadata rather then individual notes, even though additional genre-specific constraint could be introduced by users to meet their stylistic requirements.

Artificial Intelligence (AI) has gradually attracted attention in the field of artistic creation, resulting in a debate on the evaluation of AI artistic outputs. However, there is a lack of common criteria for objective artistic evaluation both of human and AI creations. This is a frequent issue in the field of dance, where different performance metrics focus either on evaluating human or computational skills separately. This work proposes a methodological approach for the artistic evaluation of both AI and human artistic creations in the field of robotic dance. First, we define a series of common initial constraints to create robotic dance choreographies in a balanced initial setting, in collaboration with a group of human dancers and choreographer. Then, we compare both creation processes through a human audience evaluation. Finally, we investigate which choreography aspects (e.g., the music genre) have the largest impact on the evaluation, and we provide useful guidelines and future research directions for the analysis of interconnections between AI and human dance creation.

Spatial segregation of sounds is a common and simple task for healthy hearing people. Unfortunately, people who suffer from partial hearing loss have great troubles in separating sound sources in crowded and noisy environments. Social isolation is the most common consequence and hearing aids are not a solution, especially in severe noisy conditions, because of their limited directionality. In this work we present the Glassense, a wearable device designed to be a complement for traditional acoustic prostheses. It exploits microphone arrays to spatially filter sounds, so that frontal speech sources are preserved, while competing noise from the sides and the back is attenuated. This behaviour, like an “acoustical lens”, changes the ratio between interesting frontal sounds and other sources, improving speech reception performance of subjects. The use of Glassense in severe noisy environments can promote social inclusion for people who suffer from partial hearing loss.