6th International ICST Conference on Body Area Networks

Research Article

Identification of Relevant Multimodal Cues to enhance Context-Aware Hearing Instruments

Download307 downloads
  • @INPROCEEDINGS{10.4108/icst.bodynets.2011.246911,
        author={Bernd Tessendorf and Peter Derleth and Manuela Feilner and Andreas Kettner and Daniel Roggen and Thomas Stiefmeier and Gerhard Tr\o{}ster},
        title={Identification of Relevant Multimodal Cues to enhance Context-Aware Hearing Instruments},
        proceedings={6th International ICST Conference on Body Area Networks},
        publisher={ICST},
        proceedings_a={BODYNETS},
        year={2012},
        month={6},
        keywords={hearing instrument body area network multimodal sensing real-life study},
        doi={10.4108/icst.bodynets.2011.246911}
    }
    
  • Bernd Tessendorf
    Peter Derleth
    Manuela Feilner
    Andreas Kettner
    Daniel Roggen
    Thomas Stiefmeier
    Gerhard Tröster
    Year: 2012
    Identification of Relevant Multimodal Cues to enhance Context-Aware Hearing Instruments
    BODYNETS
    ICST
    DOI: 10.4108/icst.bodynets.2011.246911
Bernd Tessendorf1,*, Peter Derleth2, Manuela Feilner2, Andreas Kettner1, Daniel Roggen1, Thomas Stiefmeier1, Gerhard Tröster1
  • 1: ETH Zurich
  • 2: Phonak AG
*Contact email: tessendorf@ife.ee.ethz.ch

Abstract

Today's state-of-the-art hearing instruments (HIs) adapt the sound processing only according to the user's acoustic surrounding. Acoustic ambiguities limit the set of daily life situations where HIs can support the user adequately. State-of-the-art HIs feature body area networking capabilities. Thus, body-worn sensors could be used to recognize complex user contexts and enhance next-generation HIs. In this work, we identify in a rich real-world data set the mapping between the context of the user -which can be recognized from body-worn sensors- and the user's current hearing wish. This is the foundation for the implementation of recognition systems for the specific cues in next generation HIs based on on-body sensor data. We discuss how the identified mapping allows selecting a-priori distributions for hearing wishes and HI parameters like the switching sensitivity. We conclude deducing the sensory requirements to realize next generation of networked HIs.