Smartphone-Based Open Research Platform for Hearing Improvement Studies Summary: Many advanced algorithms have been and are being developed in research labs to improve hearing of those suffering from hearing loss as part of the signal processing pipelines in hearing devices including hearing aids, cochlear implants, and sound amplifiers. Although there exist proprietary programmable platforms by hearing device companies, currently there exists no open source, programmable and portable platform that allows researchers to easily explore, run, and carry out clinical studies of research algorithms towards improving users? hearing. The objective of this project is to provide such an open source and mobile research platform thus enabling seamless evaluation of research algorithms towards enhancing hearing of those suffering from hearing loss. The successful completion of this project would have a significant impact on the deployment of advanced signal processing algorithms in future generations of hearing devices as it places a programmable, portable, flexible, and affordable research platform in the hands of researchers, audiologists, industry R&D centers, and educators to test new/existing algorithms in realistic sound environments. As illustrated in the figure shown, the proposed open source platform is based on smartphones or similar ARM-based mobile devices that nearly all users already possess. Our approach involves the development of software shells to run hearing algorithms, written in MATLAB or C, on the smartphone platform in real-time as apps in a seamless and easy-to-use way. The outcome of this project will include: (1) a user?s guide of the proposed open source platform describing a number of easy steps to take in order to run a research algorithm written in MATLAB or C on a smartphone (both Android and iPhone) in real-time, (2) a public website where a repository or library of representative speech processing algorithms source codes that go into a hearing device are provided which can be run in real-time on smartphones, and (3) a document discussing how clinical evaluations of these repository of representative research algorithms are conducted to provide a framework for carrying out clinical evaluation of any research algorithm. An indication of the broad impact of the proposed project is the support letters that our research team has received in response to the goals of this project (Starkey and Zounds Hearing companies, andthe audiologists at Dallas Ear Institute and Family Audiology).
Smartphone-Based Open Research Platform for Hearing Improvement Studies Narrative: This project aims at developing an open source research platform based on smartphones for the purpose of running speech signal processing research algorithms towards conducting hearing improvement studies. The outcome of this project enables the deployment of advanced signal processing algorithms in future generations of hearing devices including hearing aids, cochlear implants, and sound amplifiers as it places a programmable, portable, flexible, and affordable research platform in the hands of researchers, audiologists, industry R&D centers, and educators to test new/existing hearing improvement algorithms in realistic sound environments. An indication of the broad impact of the proposed project is the support letters that our research team has received in response to the goals of this project (Starkey and Zounds Hearing companies, andthe audiologists at Dallas Ear Institute and Family Audiology).
| Ganguly, Anshuman; Panahi, Issa (2018) Non-Uniform Microphone Arrays for Robust Speech Source Localization for Smartphone-Assisted Hearing Aid Devices. J Signal Process Syst 90:1415-1435 |
| Sehgal, Abhishek; Kehtarnavaz, Nasser (2018) A Convolutional Neural Network Smartphone App for Real-Time Voice Activity Detection. IEEE Access 6:9017-9026 |
| Reddy, Chandan K A; Shankar, Nikhil; Bhat, Gautam S et al. (2017) An individualized super-Gaussian single microphone Speech Enhancement for hearing aid users with smartphone as an assistive device. IEEE Signal Process Lett 24:1601-1605 |
