Sketching Audio Technologies using Vocalizations and Gestures


The goal of SkAT-VG is to develop technologies that use a designer’s vocal or/and manual gestures to create a synthetic sound that can actually be reproduced, exchanged between collaborators, edited and re- fined. The vision is that technologies that enable fast and intuive prototyping, refinement, and evaluation of product sounds will greatly facilitate the process of industrial design, boost the creativity of sound design- ers, and improve the quality of our sound environment. If successful, the project will determine significant advances in Europe in the design practices for a variety of products, such as films and multimedia shows (sound effects), games (sound-mediated sense of agency), everyday products (sonic affordances and aesthet- ics), environments (soundscapes), human-machine interfaces, and vehicles. The concepts developed during the project are also believed to be applicable to areas other than sonic sketching. In fact, once SkAT-VG would have developed the appropriate tools to infer the user’s intentions, it will be possible to consider vo- cal imitations and manual gestures more generally for expressive and intuitive human-computer interactions (including new interfaces for musical instruments and creative interfaces for non-professionals) in different fields of applications. Moreover, as it often happens when the expressive abilities of humans are exploited through technology, new unforeseeable applications and activities may spontaneously emerge.