Hearing Aid Processing Research Articles

Design and implementation of a signal processing ASIC for digital hearing aids

People with hearing loss can be benefited from assistive devices like hearing aids. This article presents the implementation of a signal processing chip for digital hearing aid applications. The functionality of the proposed design was tested in real-time using two field programmable gate arrays (FPGAs), one of them modeled as a hearing aid processor and the other as an external audio CODEC. The hearing aid processor contains an 18-band 1/3-octave ANSI S1.11 filter bank, which performs the audiogram compensation and a dynamic range compression algorithm to restrict the output signal to an acceptable loudness. The functionality of an external audio CODEC was replicated in the other FPGA to act as the analog front end circuit of a hearing aid. Serial Peripheral Interface (SPI) was used for communication between the two FPGAs. The SPI protocol was modified to make the hearing aid programmable through the data in line of the interface itself. The proposed hearing aid chip was implemented using standard cell based design flow with a 5x5 mm fixed die size intended to fit in a 48-pin package.

Preference for Combinations of Hearing Aid Signal Processing.

The purpose of this study was to determine how multiple types of signal processing activated together influence listeners' preferences. Participants were adults with mild to moderately severe sensorineural hearing loss. Stimuli were spatialized low-context sentences mixed with six-talker babble at 3 and 8 dB signal-to-noise ratios (SNRs). Stimuli were processed with three common hearing aid processing algorithms: wide dynamic range compression (WDRC), frequency compression (FC), and digital noise reduction (DNR). A full-factorial design with two levels for each algorithm (WDRC & DNR: mild versus strong; FC: ON versus OFF; clinically relevant ranges) was evaluated. Preference was measured using a paired-comparison task within a choice-based conjoint analysis framework. Remote data collection methods were used. A signal fidelity metric quantified the acoustic effects across conditions. At 3 dB SNR, participants preferred a combination of Slow WDRC and Mild DNR, although the mean preference was small (odds ratio close to 1). At both SNRs when Strong DNR was used, Fast WDRC was preferred over Slow WDRC. This may be related to signal fidelity, which was lower for the combination of Fast WDRC and Mild DNR and higher for the combination of Slow WDRC and either Mild DNR or Strong DNR. There was no effect of FC on preference or signal fidelity. WDRC and DNR together influenced both listeners' preferences and signal fidelity in the investigated listening conditions. On average, the small effect sizes suggest that minor fine-tuning adjustments to hearing aid algorithms may not result in a substantial change in clinical outcomes.

Speech Tracking in Complex Auditory Scenes with Differentiated In- and Out-Field-Of-View Processing in Hearing Aids.

In naturalistic auditory scenes, relevant information is rarely concentrated at a single location, but rather unpredictably scattered in- and out-field-of-view (in-/out-FOV). Although the parsing of a complex auditory scene is a fairly simple job for a healthy human auditory system, the uncertainty represents a major issue in the development of effective hearing aid (HA) processing strategies. Whereas traditional omnidirectional microphones (OM) amplify the complete auditory scene without enhancing signal-to-noise-ratio (SNR) between in- and out-FOV streams, directional microphones (DM) may greatly increase SNR at the cost of preventing HA users to perceive out-FOV information. The present study compares the conventional OM and DM HA settings to a split processing (SP) scheme differentiating between in- and out-FOV processing. We recorded electroencephalographic data of ten young, normal-hearing listeners who solved a cocktail-party-scenario-paradigm with continuous auditory streams and analyzed neural tracking of speech with a stimulus reconstruction (SR) approach. While results for all settings exhibited significantly higher SR accuracies for attended in-FOV than unattended out-FOV streams, there were distinct differences between settings. In-FOV SR performance was dominated by DM and SP and out-FOV SR accuracies were significantly higher for SP compared to OM and DM. Our results demonstrate the potential of a SP approach to combine the advantages of traditional OM and DM settings without introduction of significant compromises.

Influence of Audibility and Distortion on Recognition of Reverberant Speech for Children and Adults with Hearing Aid Amplification.

Adults and children with sensorineural hearing loss (SNHL) have trouble understanding speech in rooms with reverberation when using hearing aid amplification. While the use of amplitude compression signal processing in hearing aids may contribute to this difficulty, there is conflicting evidence on the effects of amplitude compression settings on speech recognition. Less clear is the effect of a fast release time for adults and children with SNHL when using compression ratios derived from a prescriptive procedure. The aim of the study is to determine whether release time impacts speech recognition in reverberation for children and adults with SNHL and to determine if these effects of release time and reverberation can be predicted using indices of audibility or temporal and spectral distortion. This is a quasi-experimental cohort study. Participants used a hearing aid simulator set to the Desired Sensation Level algorithm m[i/o] for three different amplitude compression release times. Reverberation was simulated using three different reverberation times. Participants were 20 children and 16 adults with SNHL. Participants were seated in a sound-attenuating booth and then nonsense syllable recognition was measured. Predictions of speech recognition were made using indices of audibility, temporal distortion, and spectral distortion and the effects of release time and reverberation were analyzed using linear mixed models. While nonsense syllable recognition decreased in reverberation release time did not significantly affect nonsense syllable recognition. Participants with lower audibility were more susceptible to the negative effect of reverberation on nonsense syllable recognition. We have extended previous work on the effects of reverberation on aided speech recognition to children with SNHL. Variations in release time did not impact the understanding of speech. An index of audibility best predicted nonsense syllable recognition in reverberation and, clinically, these results suggest that patients with less audibility are more susceptible to nonsense syllable recognition in reverberation.

Long-Term Effects of Hearing Aid Use on Auditory Spectral Discrimination and Temporal Envelope Sensitivity and Speech Perception in Noise.

Background : The aims of this study were to evaluate the long-term effects of hearing-aid use on auditory spectral discrimination, temporal envelope sensitivity, and speech perception ability and to determine whether hearing performance changes with the duration of hearing-aid use.Methods: The study included 13 elderly participants (64.15 ± 9.87 years) who had used hearing-aids for 12 months in everyday life. We compared the auditory performance without hearing-aids at the time of pre-fitting with the auditory performance with hearing-aids at 1 month and 12 months after fitting. Three different psychoacoustic measurements were made at their most comfortable levels to exclude the effect of amplification: (1) spectral-ripple discrimination, (2) temporal modulation detection, and (3) speech recognition in white noise.Results: Repeated-measures analysis of variance demonstrated that the duration of hearing-aid use significantly affected spectral-ripple discrimination thresholds and 100 Hz temporal modulation detection threshold (P < .05). Post hoc tests revealed that the improvements in spectral discrimination in the early post-fitting stage (1 month) did not seem to increase over the period of hearing-aid use, whereas the temporal envelope sensitivity improved continuously over time (up to 12 months).Conclusion: These results imply that hearing-aid users adapt to hearing-aid processing for spectral discrimination immediately, whereas they need time to adapt to hearing-aid processing for temporal envelope sensitivity. Alternatively, long-term hearing-aid use could induce positive plastic changes exclusively in terms of temporal envelope sensitivity.

Hearing-Aid Directionality Improves Neural Speech Tracking in Older Hearing-Impaired Listeners.

In recent years, a growing body of literature has explored the effect of hearing impairment on the neural processing of speech, particularly related to the neural tracking of speech envelopes. However, only limited work has focused on the potential usage of the method for evaluating the effect of hearing aids designed to amplify and process the auditory input provided to hearing-impaired listeners. The current study investigates how directional sound processing in hearing-aids, denoted directionality, affects the neural tracking and encoding of speech in EEG recorded from 11 older hearing-impaired listeners. Behaviorally, the task performance improved when directionality was applied, while subjective ratings of listening effort were not affected. The reconstruction of the to-be-attended speech envelopes improved significantly when applying directionality, as well as when removing the background noise altogether. When inspecting the modelled response of the neural encoding of speech, a faster transition was observed between the early bottom-up response and the later top-down attentional-driven responses when directionality was applied. In summary, hearing-aid directionality affects both the neural speech tracking and neural encoding of to-be-attended speech. This result shows that hearing-aid signal processing impacts the neural processing of sounds and that neural speech tracking is indicative of the benefits associated with applying hearing-aid processing algorithms.

Speech recognition with a hearing-aid processing scheme combining beamforming with mask-informed speech enhancement.

A signal processing approach combining beamforming with mask-informed speech enhancement was assessed by measuring sentence recognition in listeners with mild-to-moderate hearing impairment in adverse listening conditions that simulated the output of behind-the-ear hearing aids in a noisy classroom. Two types of beamforming were compared: binaural, with the two microphones of each aid treated as a single array, and bilateral, where independent left and right beamformers were derived. Binaural beamforming produces a narrower beam, maximising improvement in signal-to-noise ratio (SNR), but eliminates the spatial diversity that is preserved in bilateral beamforming. Each beamformer type was optimised for the true target position and implemented with and without additional speech enhancement in which spectral features extracted from the beamformer output were passed to a deep neural network trained to identify time-frequency regions dominated by target speech. Additional conditions comprising binaural beamforming combined with speech enhancement implemented using Wiener filtering or modulation-domain Kalman filtering were tested in normally-hearing (NH) listeners. Both beamformer types gave substantial improvements relative to no processing, with significantly greater benefit for binaural beamforming. Performance with additional mask-informed enhancement was poorer than with beamforming alone, for both beamformer types and both listener groups. In NH listeners the addition of mask-informed enhancement produced significantly poorer performance than both other forms of enhancement, neither of which differed from the beamformer alone. In summary, the additional improvement in SNR provided by binaural beamforming appeared to outweigh loss of spatial information, while speech understanding was not further improved by the mask-informed enhancement method implemented here.

Актуальные проблемы в лечении глубокой сенсоневральной тугоухости и глухоты в Кыргызстане

This article presents the main issues of the relevance of the spread of severe hearing loss and deafness in Kyrgyzstan, leading to permanent disability of patients, especially children. Despite significant technological progress and constant improvement of digital sound processing for cochlear implantation and hearing aids, in Kyrgyzstan, for a number of reasons, there are significant difficulties for their widespread implementation due to the lack of necessary government programs and appropriate funding.

Designs, Experiments, and Applications of Multichannel Structures for Hearing Aids

The structures of common multichannel processing for hearing aids include equal bandwidth (BW) finite impulse response (FIR) filter bank, nonuniform BW FIR filter bank, and fast Fourier transform (FFT) plus inverse FFT (IFFT). This paper analyzes their operation principles, indicates the design methods by means of MATLAB R2018b resources, and describes the main characteristics: synthetical ripple, bank filters’ group delays, and individual filter sidelobe attenuation. Three schemes are proposed: equal BW sixteen-filter bank, logarithmic BW eight-filter bank, and 128-point FFT plus IFFT with overlap-add operation. To build the experimental modules, we introduce the settings of spectrum scopes, the acquirement of realistic speech and noises, and the gain enhancing/reducing needs of hearing aid features; the characteristics of synthetical outputs confirm precise control ability of the multichannel modules and differences between the three schemes. Subsequently, this paper illustrates two applications of the multichannel structures in hearing aids, the equal BW sixteen-filter bank with spectral subtraction (SS) for an artificial intelligence (AI) noise reduction (NR) and 128-point FFT plus IFFT spectral distortion removal for a directional microphone (DM). In Amy’s speech mixed with ringing, milk steamer, and strong wind noises separately, the SS processor improves signal-noise-ratio (SNR) by 6.5 to 15.9 dB. By measuring waveforms and spectra at the DM input and output, the DM system seamlessly removes the spectral distortion.

Binaural Signal Processing in Hearing Aids.

For many years, clinicians have understood the advantages of listening with two ears compared with one. In addition to improved speech intelligibility in quiet, noisy, and reverberant environments, binaural versus monaural listening improves perceived sound quality and decreases the effort listeners must expend to understand a target voice of interest or to monitor a multitude of potential target voices. For most individuals with bilateral hearing impairment, the body of evidence collected across decades of research has also found that the provision of two compared with one hearing aid yields significant benefit for the user. This article briefly summarizes the major advantages of binaural compared with monaural hearing, followed by a detailed description of the related technological advances in modern hearing aids. Aspects related to the communication and exchange of data between the left and right hearing aids are discussed together with typical algorithmic approaches implemented in modern hearing aids.

A comparison of speech intelligibility and subjective quality with hearing-aid processing in older adults with hearing loss

Objective This study characterised the relationship between speech intelligibility and quality in listeners with hearing loss for a range of hearing-aid processing settings and acoustic conditions. Design Binaural speech intelligibility scores and quality ratings were measured for sentences presented in babble noise and processed through a hearing-aid simulation. The intelligibility–quality relationship was investigated by (1) assessing the effects of experimental conditions on each task; (2) directly comparing intelligibility scores and quality ratings for each participant across the range of conditions; and (3) comparing the association between signal envelope fidelity (represented by a cepstral correlation metric) and intelligibility and quality. Study sample Participants were 15 adults (7 females; age range 59–81 years) with mild to moderately severe sensorineural hearing loss. Results Intelligibility and quality showed a positive association both with each other and with changes to signal fidelity introduced by the entire acoustic and signal-processing system including the additive noise and the hearing-aid output. As signal fidelity decreased, quality ratings changed at a slower rate than intelligibility scores. Individual psychometric functions were more variable for quality compared to intelligibility. Conclusions Variability in the intelligibility–quality relationship reinforces the importance of measuring both intelligibility and quality in clinical hearing-aid fittings.

Cognitive Hearing Science: Three Memory Systems, Two Approaches, and the Ease of Language Understanding Model.

Purpose The purpose of this study was to conceptualize the subtle balancing act between language input and prediction (cognitive priming of future input) to achieve understanding of communicated content. When understanding fails, reconstructive postdiction is initiated. Three memory systems play important roles: working memory (WM), episodic long-term memory (ELTM), and semantic long-term memory (SLTM). The axiom of the Ease of Language Understanding (ELU) model is that explicit WM resources are invoked by a mismatch between language input-in the form of rapid automatic multimodal binding of phonology-and multimodal phonological and lexical representations in SLTM. However, if there is a match between rapid automatic multimodal binding of phonology output and SLTM/ELTM representations, language processing continues rapidly and implicitly. Method and Results In our first ELU approach, we focused on experimental manipulations of signal processing in hearing aids and background noise to cause a mismatch with LTM representations; both resulted in increased dependence on WM. Our second-and main approach relevant for this review article-focuses on the relative effects of age-related hearing loss on the three memory systems. According to the ELU, WM is predicted to be frequently occupied with reconstruction of what was actually heard, resulting in a relative disuse of phonological/lexical representations in the ELTM and SLTM systems. The prediction and results do not depend on test modality per se but rather on the particular memory system. This will be further discussed. Conclusions Related to the literature on ELTM decline as precursors of dementia and the fact that the risk for Alzheimer's disease increases substantially over time due to hearing loss, there is a possibility that lowered ELTM due to hearing loss and disuse may be part of the causal chain linking hearing loss and dementia. Future ELU research will focus on this possibility.

Towards Personalized Auditory Models: Predicting Individual Sensorineural Hearing-Loss Profiles From Recorded Human Auditory Physiology.

Over the past decades, different types of auditory models have been developed to study the functioning of normal and impaired auditory processing. Several models can simulate frequency-dependent sensorineural hearing loss (SNHL) and can in this way be used to develop personalized audio-signal processing for hearing aids. However, to determine individualized SNHL profiles, we rely on indirect and noninvasive markers of cochlear and auditory-nerve (AN) damage. Our progressive knowledge of the functional aspects of different SNHL subtypes stresses the importance of incorporating them into the simulated SNHL profile, but has at the same time complicated the task of accomplishing this on the basis of noninvasive markers. In particular, different auditory-evoked potential (AEP) types can show a different sensitivity to outer-hair-cell (OHC), inner-hair-cell (IHC), or AN damage, but it is not clear which AEP-derived metric is best suited to develop personalized auditory models. This study investigates how simulated and recorded AEPs can be used to derive individual AN- or OHC-damage patterns and personalize auditory processing models. First, we individualized the cochlear model parameters using common methods of frequency-specific OHC-damage quantification, after which we simulated AEPs for different degrees of AN damage. Using a classification technique, we determined the recorded AEP metric that best predicted the simulated individualized cochlear synaptopathy profiles. We cross-validated our method using the data set at hand, but also applied the trained classifier to recorded AEPs from a new cohort to illustrate the generalizability of the method.

Perceived Sound Quality Dimensions Influencing Frequency-Gain Shaping Preferences for Hearing Aid-Amplified Speech and Music.

Hearing aids are typically fitted using speech-based prescriptive formulae to make speech more intelligible. Individual preferences may vary from these prescriptions and may also vary with signal type. It is important to consider what motivates listener preferences and how those preferences can inform hearing aid processing so that assistive listening devices can best be tailored for hearing aid users. Therefore, this study explored preferred frequency-gain shaping relative to prescribed gain for speech and music samples. Preferred gain was determined for 22 listeners with mild sloping to moderately severe hearing loss relative to individually prescribed amplification while listening to samples of male speech, female speech, pop music, and classical music across low-, mid-, and high-frequency bands. Samples were amplified using a fast-acting compression hearing aid simulator. Preferences were determined using an adaptive paired comparison procedure. Listeners then rated speech and music samples processed using prescribed and preferred shaping across different sound quality descriptors. On average, low-frequency gain was significantly increased relative to the prescription for all stimuli and most substantially for pop and classical music. High-frequency gain was decreased significantly for pop music and male speech. Gain adjustments, particularly in the mid- and high-frequency bands, varied considerably between listeners. Music preferences were driven by changes in perceived fullness and sharpness, whereas speech preferences were driven by changes in perceived intelligibility and loudness. The results generally support the use of prescribed amplification to optimize speech intelligibility and alternative amplification for music listening for most listeners.

The Type of Noise Influences Quality Ratings for Noisy Speech in Hearing Aid Users.

Purpose The overall goal of the current study was to determine whether noise type plays a role in perceptual quality ratings. We compared quality ratings using various noise types and signal-to-noise ratio (SNR) ranges using hearing aid simulations to consider the effects of hearing aid processing features. Method Ten older adults with bilateral mild to moderately severe sensorineural hearing loss rated the sound quality of sentences processed through a hearing aid simulation and presented in the presence of five different noise types (six-talker babble, three-talker conversation, street traffic, kitchen, and fast-food restaurant) at four SNRs (3, 8, 12, and 20 dB). Results Everyday noise types differentially affected sound quality ratings even when presented at the same SNR: Kitchen and three-talker noises were rated significantly higher than restaurant, traffic, and multitalker babble, which were not different from each other. The effects of noise type were most pronounced at poorer SNRs. Conclusions The findings of this study showed that noise types differentially affected sound quality ratings. The differences we observed were consistent with the acoustic characteristics of the noise types. Noise types having lower envelope fluctuations yielded lower quality ratings than noise types characterized by sporadic high-intensity events at the same SNR.

Effects of Directionality, Compression, and Working Memory on Speech Recognition.

Previous research has shown that the association between hearing aid-processed speech recognition and individual working memory ability becomes stronger in more challenging conditions (e.g., higher background noise levels) and with stronger hearing aid processing (e.g., fast-acting wide dynamic range compression, WDRC). To date, studies have assumed omnidirectional microphone settings and collocated speech and noise conditions to study such relationships. Such conditions fail to recognize that most hearing aids are fit with directional processing that may improve the signal to noise ratio (SNR) and speech recognition in spatially separated speech and noise conditions. Here, we considered the possibility that directional processing may reduce the signal distortion arising from fast-acting WDRC and in turn influence the relationship between working memory ability and speech recognition with WDRC processing. The combined effects of hearing aid processing (WDRC and directionality) and SNR were quantified using a signal modification metric (cepstral correlation), which measures temporal envelope changes in the processed signal with respect to a linearly amplified reference. It was hypothesized that there will be a weaker association between working memory ability and speech recognition for hearing aid processing conditions that result in overall less signal modification (i.e., fewer changes to the processed envelope). Twenty-three individuals with bilateral, mild to moderately severe sensorineural hearing loss participated in the study. Participants were fit with a commercially available hearing aid, and signal processing was varied in two dimensions: (1) Directionality (omnidirectional [OMNI] versus fixed-directional [DIR]), and (2) WDRC speed (fast-acting [FAST] versus slow-acting [SLOW]). Sentence recognition in spatially separated multi-talker babble was measured across a range of SNRs: 0 dB, 5 dB, 10 dB, and quiet. Cumulative signal modification was measured with individualized hearing aid settings, for all experimental conditions. A linear mixed-effects model was used to determine the relationship between speech recognition, working memory ability, and cumulative signal modification. Signal modification results showed a complex relationship between directionality and WDRC speed, which varied by SNR. At 0 and 5 dB SNRs, signal modification was lower for SLOW than FAST regardless of directionality. However, at 10 dB SNR and in the DIR listening condition, there was no signal modification difference between FAST and SLOW. Consistent with previous studies, the association of speech recognition in noise with working memory ability depended on the level of signal modification. Contrary to the hypothesis above, however, there was a significant association of speech recognition with working memory only at lower levels of signal modification, and speech recognition increased at a faster rate for individuals with better working memory as signal modification decreased with DIR and SLOW. This research suggests that working memory ability remains a significant predictor of speech recognition when WDRC and directionality are applied. Our findings revealed that directional processing can reduce the detrimental effect of fast-acting WDRC on speech cues at higher SNRs, which affects speech recognition ability. Contrary to some previous research, this study showed that individuals with better working memory ability benefitted more from a decrease in signal modification than individuals with poorer working memory ability.

Effects of hearing aid processing on speech intelligibility in virtual restaurant settings

Hearing-impaired listeners struggle to understand speech in complex environments like restaurants. Environmental factors (signal-to-noise ratio and reverberation time) and hearing aid processing (digital noise reduction and wide dynamic range compression [WDRC]) have been shown to affect speech intelligibility in these contexts. We examine the independent and synergistic effects of these environmental factors and processing strategies on speech intelligibility. Virtual space techniques were used to build a virtual restaurant. The target talker was located directly in front of the listener and competing talkers were located to the listener’s right in various positions around the restaurant. Signal-to-noise ratio was varied randomly, centered on 0 dB with a standard deviation of 2 dB. Reverberation time was either 0.8 or 1.8 s. Hearing aid processing was simulated using custom software. WDRC was either fast or slow with the following attack/release times: 5/50 ms and 100/2000 ms. Digital noise reduction was either on or off. Customized gain and frequency shaping were applied to the signals. Listeners heard low-context sentences through insert earphones and repeated the target sentence. Responses were scored based on the number of correctly repeated keywords. Preliminary results show that the effect of WDRC depended on reverberation time. [Work supported by NIH.]

Effects of Directional Microphone and Noise Reduction on Subcortical and Cortical Auditory-Evoked Potentials in Older Listeners With Hearing Loss.

Understanding how signal processing influences neural activity in the brain with hearing loss is relevant to the design and evaluation of features intended to alleviate speech-in-noise deficits faced by many hearing aid wearers. Here, we examine whether hearing aid processing schemes that are designed to improve speech-in-noise intelligibility (i.e., directional microphone and noise reduction) also improve electrophysiological indices of speech processing in older listeners with hearing loss. The study followed a double-blind within-subjects design. A sample of 19 older adults (8 females; mean age = 73.6 years, range = 56-86 years; 17 experienced hearing aid users) with a moderate to severe sensorineural hearing impairment participated in the experiment. Auditory-evoked potentials associated with processing in cortex (P1-N1-P2) and subcortex (frequency-following response) were measured over the course of two 2-hour visits. Listeners were presented with sequences of the consonant-vowel syllable /da/ in continuous speech-shaped noise at signal to noise ratios (SNRs) of 0, +5, and +10 dB. Speech and noise stimuli were pre-recorded using a Knowles Electronics Manikin for Acoustic Research (KEMAR) head and torso simulator outfitted with hearing aids programmed for each listener's loss. The study aid programs were set according to 4 conditions: (1) omnidirectional microphone, (2) omnidirectional microphone with noise reduction, (3) directional microphone, and (4) directional microphone with noise reduction. For each hearing aid condition, speech was presented from a loudspeaker located at 1 m directly in front of KEMAR (i.e., 0° in the azimuth) at 75 dB SPL and noise was presented from a matching loudspeaker located at 1 m directly behind KEMAR (i.e., 180° in the azimuth). Recorded stimulus sequences were normalized for speech level across conditions and presented to listeners over electromagnetically shielded ER-2 ear-insert transducers. Presentation levels were calibrated to match the output of listeners' study aids. Cortical components from listeners with hearing loss were enhanced with improving SNR and with use of a directional microphone and noise reduction. On the other hand, subcortical components did not show sensitivity to SNR or microphone mode but did show enhanced encoding of temporal fine structure of speech for conditions where noise reduction was enabled. These results suggest that auditory-evoked potentials may be useful in evaluating the benefit of different noise-mitigating hearing aid features.

Hearing Aids Do Not Alter Cortical Entrainment to Speech at Audible Levels in Mild-to-Moderately Hearing-Impaired Subjects.

BackgroundCortical entrainment to speech correlates with speech intelligibility and attention to a speech stream in noisy environments. However, there is a lack of data on whether cortical entrainment can help in evaluating hearing aid fittings for subjects with mild to moderate hearing loss. One particular problem that may arise is that hearing aids may alter the speech stimulus during (pre-)processing steps, which might alter cortical entrainment to the speech. Here, the effect of hearing aid processing on cortical entrainment to running speech in hearing impaired subjects was investigated.MethodologySeventeen native English-speaking subjects with mild-to-moderate hearing loss participated in the study. Hearing function and hearing aid fitting were evaluated using standard clinical procedures. Participants then listened to a 25-min audiobook under aided and unaided conditions at 70 dBA sound pressure level (SPL) in quiet conditions. EEG data were collected using a 32-channel system. Cortical entrainment to speech was evaluated using decoders reconstructing the speech envelope from the EEG data. Null decoders, obtained from EEG and the time-reversed speech envelope, were used to assess the chance level reconstructions. Entrainment in the delta- (1–4 Hz) and theta- (4–8 Hz) band, as well as wideband (1–20 Hz) EEG data was investigated.ResultsSignificant cortical responses could be detected for all but one subject in all three frequency bands under both aided and unaided conditions. However, no significant differences could be found between the two conditions in the number of responses detected, nor in the strength of cortical entrainment. The results show that the relatively small change in speech input provided by the hearing aid was not sufficient to elicit a detectable change in cortical entrainment.ConclusionFor subjects with mild to moderate hearing loss, cortical entrainment to speech in quiet at an audible level is not affected by hearing aids. These results clear the pathway for exploring the potential to use cortical entrainment to running speech for evaluating hearing aid fitting at lower speech intensities (which could be inaudible when unaided), or using speech in noise conditions.

A Review of Algorithm & Hardware Design for AI-Based Biomedical Applications.

This paper reviews the state of the arts and trends of the AI-Based biomedical processing algorithms and hardware. The algorithms and hardware for different biomedical applications such as ECG, EEG and hearing aid have been reviewed and discussed. For algorithm design, various widely used biomedical signal classification algorithms have been discussed including support vector machine (SVM), back propagation neural network (BPNN), convolutional neural networks (CNN), probabilistic neural networks (PNN), recurrent neural networks (RNN), Short-term Memory Network (LSTM), fuzzy neural network and etc. The pros and cons of the classification algorithms have been analyzed and compared in the context of application scenarios. The research trends of AI-Based biomedical processing algorithms and applications are also discussed. For hardware design, various AI-Based biomedical processors have been reviewed and discussed, including ECG classification processor, EEG classification processor, EMG classification processor and hearing aid processor. Various techniques on architecture and circuit level have been analyzed and compared. The research trends of the AI-Based biomedical processor have also been discussed.