Efficient acoustic perception for virtual AI agents

We model acoustic perception in AI agents efficiently within complex scenes with many sound events. The key idea is to employ perceptual parameters that capture how each sound event propagates through the scene to the agent's location. This naturally conforms virtual perception to human. We propose a simplified auditory masking model that limits localization capability in the presence of distracting sounds. We show that anisotropic reflections as well as the initial sound serve as useful localization cues. Our system is simple, fast, and modular and obtains natural results in our tests, letting agents navigate through passageways and portals by sound alone, and anticipate or track occluded but audible targets. Source code is provided.

Il paesaggio sonoro campano tra contemporaneità e nuove forme di progettualità turistica

Full awareness of landscape occurs when it is holistically perceived. In other words, when there is osmosis between subject and object in terms of our observing, touching, breathing and listening to the same. Contemporaneously, the diminished attention paid to information provided by acoustic perception has had the effect of generating a propensity for looking rather than listening. The contribution intends to illustrate the soundscape of Campania through the tammurriata. It is not just one of the many forms of popular music expression, but the dance contains the focal points of a complex experience of collective participation, resulting in a significant tool for territorial knowledge, capable of promoting alternative forms of tourism and sense of community.

ARTIFICIAL NEURAL NETWORK APPLICATION FOR THE TEMPORAL PROPERTIES OF ACOUSTIC PERCEPTION

Though acoustic perception is well established in literature, it seems to be insufficiently implemented in practice. Experimental results are excellent but a lot of issues arise when it comes to the application in real conditions. Using artificial neural networks makes acoustic signal processing very comfortable from the mathematical point of view. However, a great job has to be done in order to make it possible. The procedure includes data acquisition, filtering, feature extraction and selection. These techniques require much more resources than mere artificial neural networks and this represents a limiting factor for the implementation. The paper investigates the complete procedure of acoustic perception, in terms of time, in order to identify limitations.

From Bentham to Guadet: ‘Auditory Visibility’ in Nineteenth-Century Theories on Government Offices

Architectural historiography is seldom concerned with the antithetical notions of ‘noise’ and ‘silence’. In this case study, I tentatively explore the theme in the context of nineteenth-century administrative buildings. More particularly, I investigate the normative views of British and French authors concerning acoustic perception in one subtype of ‘bureaucratic’ architecture: the ministerial office building. Drawing examples from the work of, among others, ‘panopticon’ theorist Jeremy Bentham and the architect Julien Guadet, I point at the centrality of ‘sound control’ or ‘sound management’ in architectural discourses on office buildings. In the specific domain of ministerial offices, moreover, these discourses were rife with ideological views on the nature and the functioning of government itself.