A Wearable, Extensible, Open-Source Platform for Hearing Healthcare Research

Application scenarios for a mobile hearing aid demonstrator with headphone form factor

OBJECTIVE

To describe application scenarios of a mobile device that provides a practical means for showcasing potential hearing aid benefits.

DESIGN

A prototype of a hearing aid demonstrator based on circumaural headphones and a mobile signal processing platform was developed, providing core functions of a hearing aid, including several gain presets, in a hygienic, robust, and easy-to-use form factor. Speech intelligibility outcomes with the demonstrator and broadband level adaptations as potential fitting references were compared to outcomes with the own hearing aids of hearing-impaired participants. Furthermore, subjective assessments of the effect of the demonstrator were obtained at a public outreach event.

STUDY SAMPLE

20 experienced hearing aid users participated in the speech intelligibility outcome measurements. 54 citizens participated in the public outreach event.

RESULTS

Speech intelligibility measurements made with the demonstrator constituted a better predictor for typically achieved aided speech intelligibility outcomes than broadband level adaptations. Participants at the public outreach event reported that trying out the demonstrator changed their expectations of hearing aid benefits and improved their understanding of how hearing aids work.

CONCLUSION

The developed demonstrator promises to be a useful tool for showcasing and probing benefits of hearing aids in clinical, public, and educational settings.

Evaluation of a research hearing aid for audiological testing

OBJECTIVE

Open-source hearing aid (HA) research tools provide avenues for testing new audiological concepts. This study compared a wearable research HA (RHA) - the "Portable Hearing Laboratory" - to a high-end commercial HA (CHA) in terms of aided outcome. Using this RHA, it also evaluated a fitting approach based on non-individualised gain presets.

DESIGN

Using a randomised repeated-measures design, participants completed speech recognition and speech quality assessments under unaided and several aided (RHA and CHA with omnidirectional and directional microphone settings) conditions. Furthermore, two approaches for prescribing amplification were evaluated with the RHA: (1) a preset approach based on non-verified clinical gain targets calculated for three standard audiograms, and (2) a best-practice approach based on individually prescribed and verified clinical gain targets.

STUDY SAMPLE

Fifteen adults aged 50-78 years with symmetrical, mild-to-moderate sensorineural hearing losses.

RESULTS

The RHA and CHA gave similar audibility, speech recognition in quiet and in noise, and speech quality ratings in quiet and in noise. Relative to the best-practice approach, the preset approach resulted in less audibility but similar speech recognition in quiet and in noise.

CONCLUSION

The RHA appears suited for testing new audiological concepts such as preset-based approaches to HA fitting.

Real-Time Multirate Multiband Amplification for Hearing Aids

Hearing loss is a common problem affecting the quality of life for thousands of people. However, many individuals with hearing loss are dissatisfied with the quality of modern hearing aids. Amplification is the main method of compensating for hearing loss in modern hearing aids. One common amplification technique is dynamic range compression, which maps audio signals onto a person's hearing range using an amplification curve. However, due to the frequency dependent nature of the human cochlea, compression is often performed independently in different frequency bands. This paper presents a real-time multirate multiband amplification system for hearing aids, which includes a multirate channelizer for separating an audio signal into eleven standard audiometric frequency bands, and an automatic gain control system for accurate control of the steady state and dynamic behavior of audio compression as specified by ANSI standards. The spectral channelizer offers high frequency resolution with low latency of 5.4 ms and about 14× improvement in complexity over a baseline design. Our automatic gain control includes a closed-form solution for satisfying any designated attack and release times for any desired compression parameters. The increased frequency resolution and precise gain adjustment allow our system to more accurately fulfill audiometric hearing aid prescriptions.

Open community platform for hearing aid algorithm research: open Master Hearing Aid (openMHA)

open Master Hearing Aid (openMHA) was developed and provided to the hearing aid research community as an open-source software platform with the aim to support sustainable and reproducible research towards improvement and new types of assistive hearing systems not limited by proprietary software. The software offers a flexible framework that allows the users to conduct hearing aid research using tools and a number of signal processing plugins provided with the software as well as the implementation of own methods. The openMHA software is independent of a specific hardware and supports Linux, macOS and Windows operating systems as well as 32-bit and 64-bit ARM-based architectures such as used in small portable integrated systems. www.openmha.org.

Multirate Audiometric Filter Bank for Hearing Aid Devices

The frequency-dependent nature of hearing loss poses many challenges for hearing aid design. In order to compensate for a hearing aid user's unique hearing loss pattern, an input signal often needs to be separated into frequency bands, or channels, through a process called sub-band decomposition. In this paper, we present a real-time filter bank for hearing aids. Our filter bank features 10 channels uniformly distributed on the logarithmic scale, located at the standard audiometric frequencies used for the characterization and fitting of hearing aids. We obtained filters with very narrow passbands in the lower frequencies by employing multi-rate signal processing. Our filter bank offers a 9.1× reduction in complexity as compared to conventional signal processing. We implemented our filter bank on Open Speech Platform, an open-source hearing aid, and confirmed real-time operation.

SSGD: SPARSITY-PROMOTING STOCHASTIC GRADIENT DESCENT ALGORITHM FOR UNBIASED DNN PRUNING

While deep neural networks (DNNs) have achieved state-of-the-art results in many fields, they are typically over-parameterized. Parameter redundancy, in turn, leads to inefficiency. Sparse signal recovery (SSR) techniques, on the other hand, find compact solutions to overcomplete linear problems. Therefore, a logical step is to draw the connection between SSR and DNNs. In this paper, we explore the application of iterative reweighting methods popular in SSR to learning efficient DNNs. By efficient, we mean sparse networks that require less computation and storage than the original, dense network. We propose a reweighting framework to learn sparse connections within a given architecture without biasing the optimization process, by utilizing the affine scaling transformation strategy. The resulting algorithm, referred to as Sparsity-promoting Stochastic Gradient Descent (SSGD), has simple gradient-based updates which can be easily implemented in existing deep learning libraries. We demonstrate the sparsification ability of SSGD on image classification tasks and show that it outperforms existing methods on the MNIST and CIFAR-10 datasets.