Non-intrusive audio notification in emotion classified background music

Ralf Jung

In: Acoustical Society of America (Hrsg.). POMA. Meeting of the Acoustical Society of America ASA (Acoustics-2010), Joint 159th ASA Meeting and Noise-Con 2010, April 19-23, Baltimore, USA, Pages 050001-050001, Proceedings of Meetings on Acoustics (POMA), Vol. 9, No. 1, ASA, 4/2010.


In Human-Computer Interaction, audio signals are generally used for warnings and acoustic feedback. Especially in environments with many people, such signals often affect intrusively and distractive because of their differentness compared to the natural sound environment. In this paper, a novel audio notification system is presented that provides methods to notify persons individually in multi-user environments. The used audio cues are unnoticeable for others since they can be embedded seamlessly in ambient background music. A novel notification hierarchy with three signal classes is introduced to realize a personalized and a context-aware notification within the background music. For the self-composed background music, we take perceptual constraints like auditive Gestalt laws as well as results from musicology into account to influence the listeners perception. A classification model for the emotional expression of non-vocal music is also introduced in this paper. The effectiveness of the novel notification method and the plausibility of the classification model are confirmed by empirical studies. This novel non-intrusive audio notification method let users become aware of individual events while at the same time other present persons will not get distracted by the notification.


Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence