# Assistive Technologies and AI: Improving Hearing Aids Using Artificial Intelligence

May 31, 2022

[Nikolas Soriano](/content/blog?author=62686760b5a42c720cdfaeda/index.html)

## Introduction
In recent years, there has been significant discourse surrounding the development and application of AI-powered assistive technologies (AT). In a 2020 conference led by the Global Disabilities Innovation Hub (GDI Hub), a panel consisting of industry leaders, policymakers, and assistive technology users concluded that **“advances in AI offer the potential to develop and enhance [assistive technologies]”** as well as “enhance inclusion, participation, and independence for people with disabilities.” Hearing aids, an assistive technology marketed towards those with mild to moderate hearing loss, can serve as a valuable precedent for the successful integration of AI into assistive technologies.

According to the National Institute on Deafness and Other Communications Disorders (NIDCD), over 28 million adults in the United States could benefit from the use of hearing aids. However, **less than 30% of people who would benefit from hearing aids regularly use them**, a particularly worrying statistic in light of the cognitive, social, and emotional impact untreated hearing loss has been shown to engender. Studies released by the American Speech-Language-Hearing Association (ASHA) revealed that untreated hearing loss is positively correlated with increased rates of social isolation, depression, anxiety, and comorbidity with cognitive disorders - namely, Alzheimer’s and dementia. The relationship between hearing, cognition, and emotional wellbeing is complex, and while addressing hearing loss is not a panacea for these challenges,

## there is growing evidence that the use of assistive technologies such as hearing aids could improve the quality of life and decrease the rate of cognitive decline in those with hearing loss.

## Reluctance to Use Hearing Aids
Why then, is there an observable reluctance to use hearing aids? Individual reasoning varies, but a common theme among these responses is a lack of confidence in the value of hearing aids, largely due to perceived poor sound quality and underperformance in noisy environments. Although not broadly implemented, AI provides many innovative means of refining user experience and improving the acoustic performance of hearing aids.

### Understanding Hearing Loss
The **human ear**, working in tandem with the auditory cortex, **is particularly adept at isolating conversations or specific threads of auditory information in the presence of noise pollution. However,** those who use hearing aids often struggle to separate large quantities of auditory information. The difficulty stems, in part, from symptoms associated with hearing loss, but limitations of current digital hearing aid technology also play a significant role. Sensorineural hearing loss is the most common form of hearing loss, caused by damage to the inner ear or auditory nerve. This condition leads to a reduction in dynamic range and distortion of the auditory periphery. **Amplifying all sound does little to accommodate these challenges, and in fact, is likely to compound them.**

While it is not uncommon for hearing aids to incorporate some form of acoustic balancing or noise reduction technology, many of these solutions have distinct limitations. For example, wide dynamic range compression (WDRC) is often used to balance dynamic range, enhancing soft sounds while decreasing loud sounds. However, this solution reduces contrast in the sound spectrum, potentially distorting the auditory periphery by blurring the distinction between audio signals and noise.

### Limitations of Noise Reduction Technologies
**Noise reduction technologies are similarly imperfect**. Digital noise reduction (DNR) relies on the assumption that speech has a greater amplitude than noise, designed to amplify speech while attenuating noise. However, this classification fails as background noise is highly varied and can often mimic speech frequencies, leading to potential misinterpretation of sounds. Some studies have suggested that DNR provides no observed benefit to the user’s perception of speech or music.

### Advancements through Artificial Intelligence
Artificial intelligence has avoided some pitfalls by moving to more robust sound recognition algorithms. The **acoustic environmental classification (AEC)** is a machine learning approach whereby an algorithm classifies incoming sounds into various categories, enabling better sound management in various auditory environments. Companies such as Starkey Hearing Technologies use AEC to provide discrete adjustments for different sound environments, reducing the likelihood of important audio getting obscured by noise suppression.

With sufficient training data, machine learning algorithms have demonstrated the ability to classify sounds with up to 90% accuracy. Continuous refinement can lead to advanced systems that further categorize sounds with greater accuracy and mitigate challenges faced by hearing aid users.

Oticon has incorporated **deep neural networks (DNNs)** to enhance hearing aids' abilities by mimicking sensory processing that occurs in the brain. The structure of DNNs operates similarly to the auditory cortex, receiving audio input and processing it through layers, ultimately clarifying and synthesizing important auditory information.

### Personalization in Hearing Aids
Widex offers users a range of customizable settings through their hearing aids and the corresponding My Sound app. Users can select settings based on their listening intention, with machine learning algorithms enhancing the personalization of sound settings based on user preferences, improving auditory experience across many environments. This iterative approach fosters a continuously updated recommendation system, allowing for dynamic listening adjustments.

## Addressing User Experience
AI has not just improved sound quality but is also transforming hearing aids into comprehensive health monitoring tools. Evidence suggests that cognitive decline is more prevalent among individuals with hearing loss, leading to the need for active engagement in social situations. Starkey hearing aids, through their AEC, classify listening conditions and also include data logging to monitor hearing aid usage that contributes to a user’s social engagement score.

While artificial intelligence enhances functionalities in hearing aids, user adoption remains crucial for effectiveness. Improvements achieved through AI integration aim to build confidence and encourage usage among individuals hesitant about the benefits of hearing aid technology. **Ultimately, AI hearing aids symbolize the potential of combining assistive technologies with artificial intelligence**, paving the way for innovative advancements in support of those benefiting from these technologies.

## Sources
1. Holloway, C., Shawe-Taylor, J., & Moledo, A. (2021). _Powering Inclusions: Artificial Intelligence and Assistive Technology_. UCL Department of Science, Technology, Engineering, and Public Policy. [Link](https://www.ucl.ac.uk/steapp/collaborate/policy-impact-unit/current-projects/policy-brief-powering-inclusion-artificial)
2. U.S. Department of Health and Human Services. (2021, March 25). _Quick Statistics About Hearing_. National Institute of Deafness and Other Communication Disorders. [Link](https://www.nidcd.nih.gov/health/statistics/quick-statistics-hearing#8)
3. Oyler, A. (2012, January). _Untreated Hearing Loss in Adults_. American Speech-Language-Hearing Association. [Link](https://www.asha.org/articles/untreated-hearing-loss-in-adults/)
4. Sarant, J., et al. (2020). _The Effect of Hearing Aid Use on Cognition in Older Adults: Can We Delay Decline or Even Improve Cognitive Function?_. Journal of clinical medicine, 9(1), 254. [DOI](https://doi.org/10.3390/jcm9010254)
5. Bucholc, M, et al. (2022). _The impact of hearing impairment and hearing aid use on progression to mild cognitive impairment_. Alzheimer's Dement. 8(1). [DOI](https://doi.org/10.1002/trc2.12248)
6. McCormack A., & Fortnum, H. (2013). _Why do people fitted with hearing aids not wear them?_. International Journal of Audiology. 52(5), 360-368. [DOI](https://doi.org/10.3109/14992027.2013.769066)
7. Health24. (2017). _Selective hearing: How humans focus on what they want to hear_. [Link](https://www.news24.com/health24/medical/hearing-management/news/selective-hearing-how-humans-focus-on-what-they-want-to-hear-20171020)
8. _Sensorineural hearing loss_. American Speech-Language-Hearing Association. [Link](https://www.asha.org/public/hearing/sensorineural-hearing-loss/)
9. Alexander J. M. (2021). _Hearing Aid Technology to Improve Speech Intelligibility in Noise_. Seminars in hearing, 42(3), 175–185. [DOI](https://doi.org/10.1055/s-0041-1735174)
10. _Digital Noise Reduction Processing in hearing aids: How much and where?_ (2008). The Hearing Review. [Link](https://hearingreview.com/practice-building/practice-management/digital-noise-reduction-processing-in-hearing-aids-how-much-and-where)
11. Kim, H. J., et al. (2020). _Effect of Digital Noise Reduction of Hearing Aids on Music and Speech Perception_. Journal of audiology & otology, 24(4), 180–190. [DOI](https://doi.org/10.7874/jao.2020.00031)
12. Fabry, D. A., & Bhowmik, A. K. (2021). _Improving Speech Understanding and Monitoring Health with Hearing Aids Using Artificial Intelligence_. Seminars in hearing, 42(3), 295–308. [DOI](https://doi.org/10.1055/s-0041-1735136)
13. _What is a Deep Neural Network?_ (n.d.) Oticon. [Link](https://www.oticon.com/blog/what-is-a-deep-neural-network-dnn)
14. Dambroski, S. (2019). _Understanding how the brain makes sense of sound_. NSF. [Link](https://www.nsf.gov/discoveries/disc_summ.jsp?cntn_id=297993&org=NSF&from=news)
15. Moolayil, J. J. (2019). _A Layman’s Guide to Deep Neural Networks_. Towards Data Science. [Link](https://towardsdatascience.com/a-laymans-guide-to-deep-neural-networks-ddcea24847fb)
16. Santurrete, S., & Behrens, T. (2020). _The Audiology of Oticon More_ (White paper). Oticon. [Link](https://wdh01.azureedge.net/-/media/oticon/main/pdf/master/whitepaper/69619uk_wp_oticon_more_audiology.pdf?la=en&rev=BDC0&hash=D3C850D07BA5CD049F38E0FB06CDA2A6)
17. Brændgaard, M. (2020). _An Introduction to MoreSound Intelligence_ (White paper). Oticon. [Link](https://wdh01.azureedge.net/-/media/oticon/main/pdf/master/whitepaper/69674uk_tech_paper_moresound_intelligence.pdf?la=en&rev=3F19&hash=6A1037B3951F262345E45C4A725D3CC7)
18. _Would You Like Some AI Or Machine Learning With Your Hearing Aids?_ (2018). Widex Pro. [Link](https://www.widexpro.com/en-us/blog/global/ai-machine-learning-with-hearing-aids/)
19. Townsend O., et al. (2018). _Soundsense Learn-Listening Intention and Machine Learning_. The Hearing Review. [Link](https://hearingreview.com/hearing-products/hearing-aids/real-life-applications-machine-learning-hearing-aids-2#comments)
20. _The Difference Is In The Data._ (2021). Widex Pro. [Link](https://www.widexpro.com/en/blog/global/2021-09-01-my-sound-the-difference-is-in-the-data/)
21. Froehlich, M., et al. (2018). _Perception of Own Voice Wearing Hearing Aids_. Audiologyonline. [Link](https://www.audiologyonline.com/articles/perception-own-voice-wearing-hearing-22822)
22. _How Signia Improved Machine Learning in Hearing Aids._ (2019). Signia. [Link](https://www.signia-pro.com/en-ca/blog/global/2019-06-01-how-signia-improved-machine-learning-in-hearing-aids/)
23. _Signia AX Own Voice Processing 2.0._(2022). Signia. [Link](https://www.signia-library.com/scientific_marketing/signia-ax-own-voice-processing-2-0/)
24. Høydel, E.H. (2017). _A New Own Voice Processing System for Optimizing Communication_. The Hearing Review. [Link](https://hearingreview.com/practice-building/marketing/new-voice-processing-system-optimizing-communication)
25. Powell, D.S., et al. (2022). _Hearing Loss and Cognition: What We Know and Where We Need to Go_. Frontiers in Aging Neuroscience. [DOI](https://doi.org/10.3389/fnagi.2021.76940)
26. National Academies of Sciences, Engineering, and Medicine. (2020). _Social Isolation and Loneliness in Older Adults: Opportunities for the Health Care System_. The National Academies Press. [DOI](https://doi.org/10.17226/25663)