Individual Aided Speech-Recognition Performance and Predictions of Benefit for Listeners With Impaired Hearing Employing FADE

Abstract

The benefit in speech-recognition performance due to the compensation of a hearing loss can vary between listeners, even if unaided performance and hearing thresholds are similar. To accurately predict the individual performance benefit due to a specific hearing device, a prediction model is proposed which takes into account hearing thresholds and a frequency-dependent suprathreshold component of impaired hearing. To test the model, the German matrix sentence test was performed in unaided and individually aided conditions in quiet and in noise by 18 listeners with different degrees of hearing loss. The outcomes were predicted by an individualized automatic speech-recognition system where the individualization parameter for the suprathreshold component of hearing loss was inferred from tone-in-noise detection thresholds. The suprathreshold component was implemented as a frequency-dependent multiplicative noise (mimicking level uncertainty) in the feature-extraction stage of the automatic speech-recognition system. Its inclusion improved the root-mean-square prediction error of individual speech-recognition thresholds (SRTs) from 6.3 dB to 4.2 dB and of individual benefits in SRT due to common compensation strategies from 5.1 dB to 3.4 dB. The outcome predictions are highly correlated with both the corresponding observed SRTs ( R2 = .94) and the benefits in SRT ( R2 = .89) and hence might help to better understand—and eventually mitigate—the perceptual consequences of as yet unexplained hearing problems, also discussed in the context of hidden hearing loss.

Robust data-driven auditory profiling towards precision audiology

“…Although Plomp’s attenuation and distortion components are often assumed to be independent, some impairment mechanisms may, in fact, affect both speech-in-noise perception and audiometric thresholds, especially at high frequencies (Moore 2016), which is consistent with distortion type I. Schädler et al (2020) attempted to model supra-threshold auditory deficits that are independent of audibility loss. Their results suggested that reduced speech intelligibility represents an auditory perceptual deficit that may be associated with reduced tone-in-noise detection which is in agreement with the results from the current study.…”

Auditory Tests for Characterizing Hearing Deficits in Listeners With Various Hearing Abilities: The BEAR Test Battery

“…The advantage of the TEN test is that the expected masked thresholds are similar to the level of the noise (i.e., as TEN is played at 70 dB per equal rectangular bandwidth (ERB), the masked threshold is expected to be at 70 dB SPL). Although this test was originally design to detect dead cochlear regions, recent evidence suggests that tone-in-noise detection can be representative of supra-threshold deficits beyond the audiogram (Schädler et al, 2020 ).…”

Auditory tests for characterizing hearing deficits in listeners with various hearing abilities: The BEAR test battery

“…The advantage of the TEN test is that the expected masked thresholds are similar to the level of the noise (i.e., as TEN is played at 70dB per equal rectangular bandwidth (ERB), the masked threshold is expected to be at 70 dB SPL). Although this test was originally design to detect dead cochlear regions, recent evidence suggests that tone-in-noise detection can be representative of supra-threshold deficits beyond the audiogram (Schädler et al, 2020).…”