Real-life situations are hard to replicate in the laboratory and often discarded during hearing aids optimisation, leading to performance inconsistencies and user dissatisfaction. As a solution, the authors propose a tool set to incorporate real-life conditions in the design, test and fitting of hearing aids. This tool set includes a spatial audio simulation framework for generating large number of realistic situations, a machine learning algorithm focused on prominent hearing aids problems trained with the newly generated data, and a low-cost spatial audio solution for audiological clinics for improved fitting of hearing aids. The current article presents the first results of the spatial audio simulation framework compared to a reference scenario and other existent solutions in literature. First findings demonstrate that synthesized impulse responses with arbitrary source directivity combined with using hearing aid head related transfer functions, with spatial upsampling and Ambisonic domain optimizations, to generate simulated binaural audio can be a powerful tool for generating several real-life situations for further hearing aids research.
(See document for exact affiliation information.)
https://aes2.org/publications/elibrary-page/?id=22271
(286KB)
Click to purchase paper as a non-member or login as an AES member. If your company or school subscribes to the E-Library then switch to the institutional version. If you are not an AES member Join the AES. If you need to check your member status, login to the Member Portal.
