Audio assisted group detection using smartphones

In this paper we introduce a novel technique to discover groups of users sharing the same environment: a room, an office, a car. Using a smartphone device, we propose a method based on the joint usage of GPS and acoustic fingerprints, allowing to greatly improve the precision of GPS only group detection. To reach the objective, we use a novel variation of an existing audio fingerprinting algorithm with good noise tolerance, assessing it under several conditions. The method is shown to be especially effective for groups of listeners of audio and audio visual content. We finally propose an application of the method to deliver content recommendations for a specific use case, hybrid content radio, an adaptive radio service discussed in the European Broadcasting Union, allowing the enrichment of traditional broadcast linear radio with personalized and context-aware audio content.