doiSerbia

Design of a multimodal hearing system

Tessendorf Bernd (Wearable Computing Lab., ETH Zurich, Zurich, Switzerland)
Debevc Matjaz (University of Maribor, Maribor, Slovenia)
Derleth Peter (Phonak AG, Stäfa, Switzerland)
Feilner Manuela (Phonak AG, Stäfa, Switzerland)
Gravenhorst Franz (Wearable Computing Lab., ETH Zurich, Zurich, Switzerland)
Roggen Daniel (Wearable Computing Lab., ETH Zurich, Zurich, Switzerland)
Stiefmeier Thomas (Wearable Computing Lab., ETH Zurich, Zurich, Switzerland)
Tröster Gerhard (Wearable Computing Lab., ETH Zurich, Zurich, Switzerland)

Hearing instruments (HIs) have become context-aware devices that analyze the acoustic environment in order to automatically adapt sound processing to the user’s current hearing wish. However, in the same acoustic environment an HI user can have different hearing wishes requiring different behaviors from the hearing instrument. In these cases, the audio signal alone contains too little contextual information to determine the user’s hearing wish. Additional modalities to sound can provide the missing information to improve the adaption. In this work, we review additional modalities to sound in HIs and present a prototype of a newly developed wireless multimodal hearing system. The platform takes into account additional sensor modalities such as the user’s body movement and location. We characterize the system regarding runtime, latency and reliability of the wireless connection, and point out possibilities arising from the novel approach.

Keywords: multimodal hearing instrument, assistive technology