[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119183-en":3,"doc-seo-119183-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},119183,8796095461610,"Oliver","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Efficient Personalization of Amplification in Hearing Aids via Multi-band Bayesian Machine Learning","Personalized amplification in hearing aids improves user outcomes, yet existing machine-learning fitting methods often require extensive paired comparisons and lengthy training. This work introduces an efficient multi-band Bayesian machine learning approach that learns frequency-band contributions in an independent manner while using paired comparisons for training. Simulations show estimates of the hearing preference function that closely match the true preference with fewer comparisons than prior methods. Clinical testing with eight hearing-impaired subjects demonstrates personalized gain settings that are, on average, six times more preferred than standard prescriptive gains.","Efficient Personalization of Amplification in Hearing Aids via Multi  \nband Bayesian Machine Learning  \nAoxin Ni1, Edward Lobarinas2, and Nasser Kehtarnavaz1  \n1Department of Electrical and Computer Engineering  \n2Callier Center for Communication Disorders  \nUniversity of Texas at Dallas, Richardson, TX  \nAbstract— Personalization of the amplification function of hearing aids has been shown to be of benefit to hearing aid users in previous studies. Several machine learning-based personalization approaches have been introduced in the literature. This paper presents a machine learning personalization approach with the advantage of being efficient in its training based on paired comparisons which makes it practical and field deployable. The training efficiency of this approach is the result of treating frequency bands independent of one another and by simultaneously carrying out Bayesian machine learning in each band across all of the frequency bands. Simulation results indicate that this approach leads to an estimated hearing preference function close to the true hearing preference function in fewer number of paired comparisons relative to the previous machine learning approaches. In addition, a clinical experiment conducted on eight subjects with hearing impairment indicate that this training efficient personalization approach provides personalized gain settings which are on average six times more preferred over the standard prescriptive gain settings.  \nIndex Terms—Personalization of hearing aid amplification, efficient paired comparisons for hearing aid fitting, multi-band Bayesian machine learning.  \nI. INTRODUCTION  \nWidely used prescriptions of hearing aids, such as DSLv5 [1] and NAL-NL2 [2], involve setting gain values in a number of frequency bands based on a user’s audiogram. An audiogram indicates the lowest level of sound pressure level (SPL) that a person can hear across audible frequency bands in a quiet audio environment [3] . There is a need to tailor the amplification function of hearing aids to noisy audio environments that are of particular interest to an individual user. Furthermore, with the recent introduction of more affordable Over-The-Counter (OTC) hearing aids, there is a growing need for their self-adjustment [4] .  \nAny personalization or self-adjustment needs to be done ina simple and easy-to-use manner for it to be adopted by users. A complex personalization or self-adjustment involving too many “knobs” to adjust would be a major hindrance to its utilization. A number of simple methods, such as sliders, wheels, and pairwise comparisons, have been considered by researchers [5-8] . Among these methods, the pairwise comparison method is often chosen due to its simplicity in  \nhearing preference studies, e.g. [9-12] . This method places minimal cognitive load on users as it merely involves selecting one out of two options similar to the pairwise comparisons inan eye exam.  \nA number of machine learning approaches have been developed in the literature to encode pairwise comparisons ina more systematic way and to conduct personalization of the amplification function of hearing aids including the ones by our research team [13-15]. These approaches normally involve a trade-off between the size of the search space and the duration of the fitting process or training. In our latest work, the machine learning approach of Maximum Likelihood Inverse Reinforcement Learning (MLIRL) [14, 15] was introduced in order to achieve personalization of amplification in an on-the-fly or online manner. Although this approach was shown to produce personalized settings that were preferred over the standard settings by about 10 times, it required a training duration of at least one hour to go through a large number of paired comparisons. This relatively long training time poses a bottleneck that restricts deployment in the field.  \nIn this paper, a new machine learning approach is developed in order to address the above shortcomi","cbCaihLurKExRJVQ","https://ap.wps.com/l/cbCaihLurKExRJVQ","pdf",695525,1,7,"English","en",105,"# Introduction\n## Independence of Multi-band Amplification\n## Personalized Gain Bounds and Frequency Bands\n# Bayesian Learning in Each Frequency Band\n# Clinical Experiment Setup\n## Hearing Preference and Word Recognition Results\n# Conclusion","[{\"question\":\"What problem does the paper address in hearing-aid personalization?\",\"answer\":\"It targets the need to tailor hearing-aid amplification to individual users and to make personalization practical, especially for noisy environments and over-the-counter self-adjustment, without requiring complex controls or long training sessions.\"},{\"question\":\"How does the proposed method improve training efficiency?\",\"answer\":\"It performs Bayesian machine learning independently in each frequency band, reducing the number of paired comparisons needed to reach personalized settings and making online field deployment more feasible.\"},{\"question\":\"What do simulation and clinical experiments show?\",\"answer\":\"Simulations indicate that the estimated hearing preference function closely matches the true function using fewer paired comparisons than previous approaches. A clinical experiment with eight subjects shows personalized gain settings averaged about six times more preferred than standard prescriptive gains.\"}]","Efficient Personalization of Amplification in Hearing Aids via Multi-band Bayesian Machine Learning | PDF",1785722969,18,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"efficient-personalization-of-amplification-in-hearing-aids-via-multi-band-bayesian-machine-learning","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/efficient-personalization-of-amplification-in-hearing-aids-via-multi-band-bayesian-machine-learning/119183/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the paper address in hearing-aid personalization?","Question",{"text":75,"@type":76},"It targets the need to tailor hearing-aid amplification to individual users and to make personalization practical, especially for noisy environments and over-the-counter self-adjustment, without requiring complex controls or long training sessions.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the proposed method improve training efficiency?",{"text":80,"@type":76},"It performs Bayesian machine learning independently in each frequency band, reducing the number of paired comparisons needed to reach personalized settings and making online field deployment more feasible.",{"name":82,"@type":73,"acceptedAnswer":83},"What do simulation and clinical experiments show?",{"text":84,"@type":76},"Simulations indicate that the estimated hearing preference function closely matches the true function using fewer paired comparisons than previous approaches. A clinical experiment with eight subjects shows personalized gain settings averaged about six times more preferred than standard prescriptive gains.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,119,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]