openMHA presentation at DAGA2017
The project and the openMHA pre-release was presented at the
Annual Meeting of the German Acoustical Society: DAGA2017
Kiel, Germany
Abstract
Open community platform for hearing aid algorithm research
Hendrik Kayser, Tobias Herzke, Giso Grimm and Volker Hohmann
The project “Open community platform for hearing aid algorithm research” funded by the National Institutes of Health (NIH Grant 1R01DC015429-01) aims at sustainable, focused research towards improvement and new types of assistive hearing systems. To this end an open-source software platform for real-time audio signal processing will be developed and made available to the research community including a standard set of reference algorithms. Furthermore, novel algorithms for dynamic and frequency compression, auditory-scene-analysis based noise suppression and speech enhancement and feedback management will be investigated. For a realistic assessment of the benefits of hearing aid algorithms and combinations thereof, instrumental measures of performance in virtual acoustic environments of varying complexity will be included in the algorithm design and optimization. With such a quasi-standard set of benchmarks and the means to develop and integrate own signal-processing methods and measures, the platform enables comparative studies and collaborative research efforts. Beyond an implementation for PC hardware the system will also be made usable for ARM-processor based hardware to allow pre-development of wearable audio devices - so-called “hearables”. This contribution will present underlying previous work and the goals and plans of the project that has started midyear 2016.