scholarly journals The Collaboration between Hearing Aid Users and Artificial Intelligence to Optimize Sound

2021 ◽  
Vol 42 (03) ◽  
pp. 282-294
Author(s):  
Laura Winther Balling ◽  
Lasse Lohilahti Mølgaard ◽  
Oliver Townend ◽  
Jens Brehm Bagger Nielsen
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Signal Processing ◽  
Hearing Aids ◽  
Hearing Aid ◽  
Bayesian Optimization ◽  
Listening Environments ◽  
User Data ◽  
The Individual ◽  
Average User

AbstractHearing aid gain and signal processing are based on assumptions about the average user in the average listening environment, but problems may arise when the individual hearing aid user differs from these assumptions in general or specific ways. This article describes how an artificial intelligence (AI) mechanism that operates continuously on input from the user may alleviate such problems by using a type of machine learning known as Bayesian optimization. The basic AI mechanism is described, and studies showing its effects both in the laboratory and in the field are summarized. A crucial fact about the use of this AI is that it generates large amounts of user data that serve as input for scientific understanding as well as for the development of hearing aids and hearing care. Analyses of users' listening environments based on these data show the distribution of activities and intentions in situations where hearing is challenging. Finally, this article demonstrates how further AI-based analyses of the data can drive development.

scholarly journals Improving Speech Understanding and Monitoring Health with Hearing Aids Using Artificial Intelligence and Embedded Sensors

2021 ◽  
Vol 42 (03) ◽  
pp. 295-308
Author(s):  
David A. Fabry ◽  
Achintya K. Bhowmik
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Hearing Aids ◽  
Background Noise ◽  
Speech Intelligibility ◽  
Hearing Aid ◽  
Machine Learning Algorithms ◽  
Embedded Sensors ◽  
Health And Wellness ◽  
Speech Understanding

AbstractThis article details ways that machine learning and artificial intelligence technologies are being integrated in modern hearing aids to improve speech understanding in background noise and provide a gateway to overall health and wellness. Discussion focuses on how Starkey incorporates automatic and user-driven optimization of speech intelligibility with onboard hearing aid signal processing and machine learning algorithms, smartphone-based deep neural network processing, and wireless hearing aid accessories. The article will conclude with a review of health and wellness tracking capabilities that are enabled by embedded sensors and artificial intelligence.

scholarly journals New Hybrid Approach for Developing Automated Machine Learning Workflows: A Real Case Application in Evaluation of Marcellus Shale Gas Production

Fuels ◽  
2021 ◽  
Vol 2 (3) ◽  
pp. 286-303
Author(s):  
Vuong Van Pham ◽  
Ebrahim Fathi ◽  
Fatemeh Belyadi
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Shale Gas ◽  
Field Data ◽  
Marcellus Shale ◽  
Hybrid Approach ◽  
Gas Production ◽  
Bayesian Optimization ◽  
Real Field ◽  
Engineering Problems

The success of machine learning (ML) techniques implemented in different industries heavily rely on operator expertise and domain knowledge, which is used in manually choosing an algorithm and setting up the specific algorithm parameters for a problem. Due to the manual nature of model selection and parameter tuning, it is impossible to quantify or evaluate the quality of this manual process, which in turn limits the ability to perform comparison studies between different algorithms. In this study, we propose a new hybrid approach for developing machine learning workflows to help automated algorithm selection and hyperparameter optimization. The proposed approach provides a robust, reproducible, and unbiased workflow that can be quantified and validated using different scoring metrics. We have used the most common workflows implemented in the application of artificial intelligence (AI) and ML in engineering problems including grid/random search, Bayesian search and optimization, genetic programming, and compared that with our new hybrid approach that includes the integration of Tree-based Pipeline Optimization Tool (TPOT) and Bayesian optimization. The performance of each workflow is quantified using different scoring metrics such as Pearson correlation (i.e., R2 correlation) and Mean Square Error (i.e., MSE). For this purpose, actual field data obtained from 1567 gas wells in Marcellus Shale, with 121 features from reservoir, drilling, completion, stimulation, and operation is tested using different proposed workflows. A proposed new hybrid workflow is then used to evaluate the type well used for evaluation of Marcellus shale gas production. In conclusion, our automated hybrid approach showed significant improvement in comparison to other proposed workflows using both scoring matrices. The new hybrid approach provides a practical tool that supports the automated model and hyperparameter selection, which is tested using real field data that can be implemented in solving different engineering problems using artificial intelligence and machine learning. The new hybrid model is tested in a real field and compared with conventional type wells developed by field engineers. It is found that the type well of the field is very close to P50 predictions of the field, which shows great success in the completion design of the field performed by field engineers. It also shows that the field average production could have been improved by 8% if shorter cluster spacing and higher proppant loading per cluster were used during the frac jobs.

Fitting Frequency-Lowering Signal Processing Applying the American Academy of Audiology Pediatric Amplification Guideline: Updates and Protocols

2016 ◽  
Vol 27 (03) ◽  
pp. 219-236 ◽  
Author(s):  
Susan Scollie ◽  
Danielle Glista ◽  
Julie Seto ◽  
Andrea Dunn ◽  
Brittany Schuett ◽  
...  
Keyword(s):  
Signal Processing ◽  
Frequency Response ◽  
Hearing Aids ◽  
Hearing Aid ◽  
Fine Tuning ◽  
Sensation Level ◽  
Response Level ◽  
Strong Basis ◽  
Wide Range ◽  
Signal Processors

Background: Although guidelines for fitting hearing aids for children are well developed and have strong basis in evidence, specific protocols for fitting and verifying technologies can supplement such guidelines. One such technology is frequency-lowering signal processing. Children require access to a broad bandwidth of speech to detect and use all phonemes including female /s/. When access through conventional amplification is not possible, the use of frequency-lowering signal processing may be considered as a means to overcome limitations. Fitting and verification protocols are needed to better define candidacy determination and options for assessing and fine tuning frequency-lowering signal processing for individuals. Purpose: This work aims to (1) describe a set of calibrated phonemes that can be used to characterize the variation in different brands of frequency-lowering processors in hearing aids and the verification with these signals and (2) determine whether verification with these signal are predictive of perceptual changes associated with changes in the strength of frequency-lowering signal processing. Finally, we aimed to develop a fitting protocol for use in pediatric clinical practice. Study Sample: Study 1 used a sample of six hearing aids spanning four types of frequency lowering algorithms for an electroacoustic evaluation. Study 2 included 21 adults who had hearing loss (mean age 66 yr). Data Collection and Analysis: Simulated fricatives were designed to mimic the level and frequency shape of female fricatives extracted from two sources of speech. These signals were used to verify the frequency-lowering effects of four distinct types of frequency-lowering signal processors available in commercial hearing aids, and verification measures were compared to extracted fricatives made in a reference system. In a second study, the simulated fricatives were used within a probe microphone measurement system to verify a wide range of frequency compression settings in a commercial hearing aid, and 27 adult listeners were tested at each setting. The relation between the hearing aid verification measures and the listener’s ability to detect and discriminate between fricatives was examined. Results: Verification measures made with the simulated fricatives agreed to within 4 dB, on average, and tended to mimic the frequency response shape of fricatives presented in a running speech context. Some processors showed a greater aided response level for fricatives in running speech than fricatives presented in isolation. Results with listeners indicated that verified settings that provided a positive sensation level of /s/ and that maximized the frequency difference between /s/ and /∫/ tended to have the best performance. Conclusions: Frequency-lowering signal processors have measureable effects on the high-frequency fricative content of speech, particularly female /s/. It is possible to measure these effects either with a simple strategy that presents an isolated simulated fricative and measures the aided frequency response or with a more complex system that extracts fricatives from running speech. For some processors, a more accurate result may be achieved with a running speech system. In listeners, the aided frequency location and sensation level of fricatives may be helpful in predicting whether a specific hearing aid fitting, with or without frequency-lowering, will support access to the fricatives of speech.

Noise Exposure Associated With Hearing Aid Use in Industry

1996 ◽  
Vol 39 (2) ◽  
pp. 251-260 ◽  
Author(s):  
Thomas G. Dolan ◽  
James F. Maurer
Keyword(s):  
Hearing Aids ◽  
Noise Exposure ◽  
Hearing Aid ◽  
Sound Field ◽  
High Gain ◽  
Sound Level ◽  
Weighted Averages ◽  
Hearing Aid Use ◽  
Listening Environments ◽  
Level Meter

Although noise may be innocuous in many vocational environments, there is a growing concern in industry that it can reach hazardous levels when amplified by hearing aids. This study examined the daily noise exposures associated with hearing aid use in industry. This was done by both laboratory and site measurements in which hearing aids were coupled to the microphone of an integrating sound level meter or dosimeter. The former method involved the use of recorded railroad and manufacturing noise and a Bruel and Kjaer 4128 Head and Torso simulator. In the latter procedure, a worker wore one of three hearing aids coupled to a dosimeter during 8-hour shifts in a manufacturing plant. Both methods demonstrated that even when amplified by mild-gain hearing aids, noise exposures rose from time-weighted averages near 80 dBA to well above the OSHA maximum of 90 dBA. The OSHA maximum was also exceeded when moderate and high gain instruments were worn in non-occupational listening environments. The results suggest that current OSHA regulations that limit noise exposure in sound field are inappropriate for hearing aid users.

scholarly journals Listener Performance with a Novel Hearing Aid Frequency Lowering Technique

2017 ◽  
Vol 28 (09) ◽  
pp. 810-822 ◽  
Author(s):  
Benjamin J. Kirby ◽  
Judy G. Kopun ◽  
Meredith Spratford ◽  
Clairissa M. Mollak ◽  
Marc A. Brennan ◽  
...  
Keyword(s):  
Signal Processing ◽  
Hearing Loss ◽  
Speech Perception ◽  
Hearing Aids ◽  
High Frequency ◽  
Hearing Aid ◽  
Sound Quality ◽  
Processing Strategy ◽  
Listening Effort ◽  
At Home

AbstractSloping hearing loss imposes limits on audibility for high-frequency sounds in many hearing aid users. Signal processing algorithms that shift high-frequency sounds to lower frequencies have been introduced in hearing aids to address this challenge by improving audibility of high-frequency sounds.This study examined speech perception performance, listening effort, and subjective sound quality ratings with conventional hearing aid processing and a new frequency-lowering signal processing strategy called frequency composition (FC) in adults and children.Participants wore the study hearing aids in two signal processing conditions (conventional processing versus FC) at an initial laboratory visit and subsequently at home during two approximately six-week long trials, with the order of conditions counterbalanced across individuals in a double-blind paradigm.Children (N = 12, 7 females, mean age in years = 12.0, SD = 3.0) and adults (N = 12, 6 females, mean age in years = 56.2, SD = 17.6) with bilateral sensorineural hearing loss who were full-time hearing aid users.Individual performance with each type of processing was assessed using speech perception tasks, a measure of listening effort, and subjective sound quality surveys at an initial visit. At the conclusion of each subsequent at-home trial, participants were retested in the laboratory. Linear mixed effects analyses were completed for each outcome measure with signal processing condition, age group, visit (prehome versus posthome trial), and measures of aided audibility as predictors.Overall, there were few significant differences in speech perception, listening effort, or subjective sound quality between FC and conventional processing, effects of listener age, or longitudinal changes in performance. Listeners preferred FC to conventional processing on one of six subjective sound quality metrics. Better speech perception performance was consistently related to higher aided audibility.These results indicate that when high-frequency speech sounds are made audible with conventional processing, speech recognition ability and listening effort are similar between conventional processing and FC. Despite the lack of benefit to speech perception, some listeners still preferred FC, suggesting that qualitative measures should be considered when evaluating candidacy for this signal processing strategy.

scholarly journals A Perspective on the Application of Kapferer's Brand Identity Prism in the Branding Process of Hearing Aid Retail Companies

2020 ◽  
Vol 5 (3) ◽  
pp. 141-146
Author(s):  
Florian Ross
Keyword(s):  
Hearing Aids ◽  
Healthcare Professionals ◽  
Hearing Aid ◽  
Jel Classification ◽  
Brand Identity ◽  
Practical Implementation ◽  
Healthcare It ◽  
Relevant Role ◽  
The Individual ◽  
Retail Company

Objective – The aim of this paper is to develop a baseline guide for the branding of hearing aids for use by Hearing Aid Retail Companies. Methodology/Technique – The individual dimensions of Kapferer's brand identity prism were analyzed and practically applied to the branding process of a Hearing Aid Retail Company. Findings – Each dimension plays a relevant role in a consistent branding process. The study concludes that Hearing Aid Retail Companies, particularly smaller ones, should focus on branding due to increasing competition to remain competitive in the market. Novelty – This paper deals with the practical implementation of Kapferer's brand identity prism in the context of Hearing Healthcare. It offers Hearing Healthcare Professionals a framework for the branding process. Type of Paper: Secondary Article – Editorial / Perspective Piece. JEL Classification: M31, M37 Abbreviation: HARC - Hearing Aid Retail Company Keywords: Branding; Marketing; Hearing Healthcare; Kapferer´s Brand Identity Prism. Reference to this paper should be made as follows: Ross, F. 2020. A Perspective on the Application of Kapferer's Brand Identity Prism in the Branding Process of Hearing Aid Retail Companies, J. Mgt. Mkt. Review 5(3) 141 – 146. https://doi.org/10.35609/jmmr.2020.5.3(2)

scholarly journals Wind Noise Management in Hearing Aids

2021 ◽  
Vol 42 (03) ◽  
pp. 248-259
Author(s):  
Petri Korhonen
Keyword(s):  
Signal Processing ◽  
Adverse Effects ◽  
Hearing Aids ◽  
Hearing Aid ◽  
Wind Noise ◽  
Outdoor Activities ◽  
Signal Processing Algorithms ◽  
Turbulent Airflow ◽  
Processing Algorithms ◽  
Noise Management

AbstractMany hearing aid users are negatively impacted by wind noise when spending time outdoors. Turbulent airflow around hearing aid microphones caused by the obstruction of wind can result in noise that is not only perceived as annoying but may also mask desirable sounds in the listening environment, such as speech. To mitigate the adverse effects of wind noise, hearing aid developers have introduced several technological solutions to reduce the amount of wind noise at the hearing aid output. Some solutions are based on mechanical modifications; more recently, sophisticated signal processing algorithms have also been introduced. By offering solutions to the wind noise problem, these signal processing algorithms can promote more optimal use of hearing aids during outdoor activities. This article reviews how wind noise is generated in hearing aids, outlines the technological challenges in wind noise management, and summarizes the technological solutions that have been proposed and/or implemented in modern hearing aids.

Using Trainable Hearing Aids to Examine Real-World Preferred Gain

2008 ◽  
Vol 19 (10) ◽  
pp. 758-773 ◽  
Author(s):  
H Gustav Mueller ◽  
Benjamin W.Y. Hornsby ◽  
Jennifer E. Weber
Keyword(s):  
Hearing Loss ◽  
Hearing Aids ◽  
Real World ◽  
Field Trial ◽  
Hearing Aid ◽  
Volume Control ◽  
Hearing Aid Use ◽  
Start Up ◽  
Listening Environments ◽  
Few Data

Background: While there have been many studies of real-world preferred hearing aid gain, few data are available from participants using hearing aids with today's special features activated. Moreover, only limited data have been collected regarding preferred gain for individuals using trainable hearing aids. Purpose: To determine whether real-world preferred hearing aid gain with trainable modern hearing aids is in agreement with previous work in this area, and to determine whether the starting programmed gain setting influences preferred gain outcome. Research Design: An experimental crossover study. Participants were randomly assigned to one of two treatment groups. Following initial treatment, each subject crossed to the opposite group and experienced that treatment. Study Sample: Twenty-two adults with downward sloping sensorineural hearing loss served as participants (mean age 64.5; 16 males, 6 females). All were experienced users of bilateral amplification. Intervention: Using a crossover design, participants were fitted to two different prescriptive gain conditions: VC (volume control) start-up 6 dB above NAL-NL1 (National Acoustic Laboratories—Non-linear 1) target or VC start-up 6 dB below NAL-NL1 target. The hearing aids were used in a 10 to 14 day field trial for each condition, and using the VC, the participants could “train” the overall hearing aid gain to their preferred level. During the field trial, daily hearing aid use was logged, as well as the listening situations experienced by the listeners based on the hearing instrument's acoustic scene analysis. The participants completed a questionnaire at the start and end of each field trial in which they rated loudness perceptions and their satisfaction with aided loudness levels. Results: Because several participants potentially experienced floor or ceiling effects for the range of trainable gain, the majority of the statistical analysis was conducted using 12 of the 22 participants. For both VC-start conditions, the trained preferred gain differed significantly from the NAL-NL1 prescriptive targets. More importantly, the initial start-up gain significantly influenced the trained gain; the mean preferred gain for the +6 dB start condition was approximately 9 dB higher than the preferred gain for the −6 dB start condition, and this difference was statistically significant (p < .001). Partial eta squared (η2) = 0.919, which is a large effect size.Deviation from the NAL-NL1 target was not significantly influenced by the time spent in different listening environments, amount of hearing aid use during the trial period, or amount of hearing loss. Questionnaire data showed more appropriate ratings for loudness and higher satisfaction with loudness for the 6 dB below target VC-start condition. Conclusions: When trainable hearing aids are used, the initial programmed gain of hearing instruments can influence preferred gain in the real world.

What Is Important for Hearing Aid Satisfaction? Application of the Expectancy-Disconfirmation Model

2014 ◽  
Vol 25 (07) ◽  
pp. 644-655 ◽  
Author(s):  
Carly Meyer ◽  
Louise Hickson ◽  
Asad Khan ◽  
David Walker
Keyword(s):  
Research Design ◽  
Hearing Aids ◽  
Consumer Satisfaction ◽  
Hearing Aid ◽  
Hearing Ability ◽  
Expected Performance ◽  
Data Collection And Analysis ◽  
Listening Environments ◽  
Expectancy Disconfirmation ◽  
Hearing Aid Benefit

Background: Between 68.1–89.5% of clients report that they are satisfied with their hearing aids. Two variables that are thought to contribute to dissatisfaction with hearing aids are product performance, and a mismatch between performance and client prefitting expectations about hearing-aid performance (i.e., disconfirmation). A focus on variables related to satisfaction is relevant to improving hearing rehabilitation services. Purpose: The aim of this study was to determine if measures of hearing-aid performance and disconfirmation, specifically related to hearing ability and hearing-aid problems, were associated with overall hearing-aid satisfaction among a sample of hearing-aid users. Research Design: A retrospective research design was employed. Study Sample: A total of 123 individuals participated in the study (57% male; mean age: 72 yr). All participants owned hearing aids. Data Collection and Analysis: A personal details questionnaire and the Profile of Hearing Aid Consumer Satisfaction questionnaire (Wong et al, 2009) were completed by participants, 3–12 mo after they obtained hearing aids. Overall hearing-aid satisfaction was a dichotomized variable (satisfaction vs. dissatisfaction); therefore, logistic regression modeling was applied to the data to determine which variables were associated with overall hearing-aid satisfaction. Results: Sixty-one percent of the sample reported that they were satisfied with their hearing aids. Hearing-aid satisfaction was associated with the ability to hear with hearing aids and better-than-expected performance in this same area; fewer hearing-aid problems; and fewer problems with hearing-aid manipulation, hearing-aid appearance, and wearer discomfort than were anticipated before hearing-aid fitting. Conclusions: It is recommended that to improve hearing-aid satisfaction, clinicians should ensure optimal hearing-aid benefit in the listening situations that the person with hearing impairment most wants to hear better; reduce the likelihood of hearing-aid problems occurring; and promote positive disconfirmation (performance exceeds expectations) with respect to both hearing ability and hearing-aid performance through the education of clients about the likely benefits of hearing aids in a variety of listening environments, and the potential problems they could face with hearing-aid manipulation and wearer discomfort.

Sign in / Sign up

Export Citation Format

Share Document