Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2020 May:2020:223-233.
doi: 10.1145/3421937.3422017.

Open Speech Platform: Democratizing Hearing Aid Research

Dhiman Sengupta  1 , Arthur Boothroyd  2 , Tamara Zubatiy  3 , Cagri Yalcin  1 , Dezhi Hong  1 , Sean K Hamilton  1 , Rajesh Gupta  1 , Harinath Garudadri  1
Affiliations

Open Speech Platform: Democratizing Hearing Aid Research

Dhiman Sengupta et al. Int Conf Pervasive Comput Technol Healthc. 2020 May.

Abstract

Hearing aids help overcome the challenges associated with hearing loss, and thus greatly benefit and improve the lives of those living with hearing-impairment. Unfortunately, there is a lack of adoption of hearing aids among those that can benefit from hearing aids. Hearing researchers and audiologists are trying to address this problem through their research. However, the current proprietary hearing aid market makes it difficult for academic researchers to translate their findings into commercial use. In order to abridge this gap and accelerate research in hearing health care, we present the design and implementation of the Open Speech Platform (OSP), which consists of a co-design of open-source hardware and software. The hardware meets the industry standards and enables researchers to conduct experiments in the field. The software is designed with a systematic and modular approach to standardize algorithm implementation and simplify user interface development. We evaluate the performance of OSP regarding both its hardware and software, as well as demonstrate its usefulness via a self-fitting study involving human participants.

Keywords: digital signal processing; hearing aids; human study; open source; real-time.

PubMed Disclaimer

Figures

Figure 1:
Figure 1:
Overview of the Open Speech Platform (OSP): OSP consists of both open-sourced hardware that meets the industry standards and software equipped with open, modular architecture and amenable user interfaces as well as functionality.
Figure 2:
Figure 2:
Architecture of real-time master hearing aid.
Figure 3:
Figure 3:
Digital signal processing path for the reference RT-MHA implementation, comprised of audio resampling, sub-band filtering, speech enhancement, wide dynamic range compression, and feedback path estimation as well as feedback cancellation.
Figure 4:
Figure 4:
Example graphical user interface for adjusting the reference design, mainly for researchers.
Figure 5:
Figure 5:
The BTE-RIC hearing aid developed for both the lab-based system and the portable system.
Figure 6:
Figure 6:
a) Lab-based system consisting of a laptop (Mac), an audio converter box, a break out board, and a hearing aid. b) The portable system connected to two hearing aids. c) Annotated PCB view of the daughterboard that attaches to the the DragonBoard 410c SBC.
Figure 7:
Figure 7:
The probability distribution (PDF) and cumulative distribution (CDF) of time required for the Real-Time Engine to process audio data packets over one-hour period under different request rates; it is capable to process data with no latency.
Figure 8:
Figure 8:
Apparatus used for the SFP study. The arrows represent the information flow from the listener interface, via WiFi, to the Portable OSP to tune the WRDC.
Figure 9:
Figure 9:
Ratings (in histograms) by the participants in the usability study, regarding a) aesthetics and form of the portable OSP device; b) sound quality; c) sound quality of the portable OSP compared to their own hearing aids; d) level of ease-to-use of the web-app; and e) whether they are willing to participate in a research project with the portable OSP.
See this image and copyright information in PMC

References

    1. Boothroyd Arthur, Kirsch Christine, Mackersie Carol, Painter Shaelyn, and Garudadri Harinath. 2019. Usability assessment of a wearable speech-processing platform. The Journal of the Acoustical Society of America 146, 4 (2019), 2878–2878.
    1. Boothroyd Arthur and Mackersie Carol. 2017. A “Goldilocks” approach to hearingaid self-fitting: User interactions. American journal of audiology 26, 3S (2017), 430–435. - PMC - PubMed
    1. Doclo Simon, Gannot Sharon, Moonen Marc, Spriet Ann, Haykin Simon, and Liu KJ Ray. 2008. Acoustic beamforming for hearing aid applications. Handbook on array processing and sensor networks (2008), 269–302.
    1. Doumler Timur. 2015. CppCon 2015: Timur Doumler “C++ in the Audio Industry” https://www.youtube.com/watch?v=boPEO2auJj4
    1. Knowles Electronics. 2009. RVA-90020-NXX Datasheet