{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T17:44:57Z","timestamp":1767203097976,"version":"build-2238731810"},"reference-count":32,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2022,2,21]],"date-time":"2022-02-21T00:00:00Z","timestamp":1645401600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neurosci."],"abstract":"<jats:p>Hearing-aid (HA) prescription rules (such as NAL-NL2, DSL-v5, and CAM2) are used by HA audiologists to define initial HA settings (e.g., insertion gains, IGs) for patients. This initial fitting is later individually adjusted for each patient to improve clinical outcomes in terms of speech intelligibility and listening comfort. During this fine-tuning stage, speech-intelligibility tests are often carried out with the patient to assess the benefits associated with different HA settings. As these tests tend to be time-consuming and performance on them depends on the patient's level of fatigue and familiarity with the test material, only a limited number of HA settings can be explored. Consequently, it is likely that a suboptimal fitting is used for the patient. Recent studies have shown that automatic speech recognition (ASR) can be used to predict the effects of IGs on speech intelligibility for patients with age-related hearing loss (ARHL). The aim of the present study was to extend this approach by optimizing, in addition to IGs, compression thresholds (CTs). However, increasing the number of parameters to be fitted increases exponentially the number of configurations to be assessed. To limit the number of HA settings to be tested, three random-search (RS) genetic algorithms were used. The resulting new HA fitting method, combining ASR and RS, is referred to as \u201cobjective prescription rule based on ASR and random search\" (OPRA-RS). Optimal HA settings were computed for 12 audiograms, representing average and individual audiometric profiles typical for various levels of ARHL severity, and associated ASR performances were compared to those obtained with the settings recommended by CAM2. Each RS algorithm was run twice to assess its reliability. For all RS algorithms, ASR scores obtained with OPRA-RS were significantly higher than those associated with CAM2. Each RS algorithm converged on similar optimal HA settings across repetitions. However, significant differences were observed between RS algorithms in terms of maximum ASR performance and processing costs. These promising results open the way to the use of ASR and RS algorithms for the fine-tuning of HAs with potential speech-intelligibility benefits for the patient.<\/jats:p>","DOI":"10.3389\/fnins.2022.779048","type":"journal-article","created":{"date-parts":[[2022,2,21]],"date-time":"2022-02-21T01:54:16Z","timestamp":1645408456000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["OPRA-RS: A Hearing-Aid Fitting Method Based on Automatic Speech Recognition and Random Search"],"prefix":"10.3389","volume":"16","author":[{"given":"Libio","family":"Gon\u00e7alves Braz","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lionel","family":"Fontan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Julien","family":"Pinquier","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael A.","family":"Stone","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christian","family":"F\u00fcllgrabe","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2022,2,21]]},"reference":[{"key":"B1","volume-title":"American National Standard: Methods for Calculation of the Speech Intelligibility Index","year":"1997"},{"key":"B2","doi-asserted-by":"publisher","first-page":"268","DOI":"10.1145\/937503.937505","article-title":"Metaheuristics in combinatorial optimization: overview and conceptual comparison","volume":"35","author":"Blum","year":"2001","journal-title":"ACM Comput. Surveys"},{"key":"B3","doi-asserted-by":"publisher","first-page":"430","DOI":"10.1044\/2017_AJA-16-0125","article-title":"A \u201cGoldilocks\u201dproblem approach to hearing-aid self-fitting: User interactions","volume":"26","author":"Boothroyd","year":"2017","journal-title":"Am. J. Audiol."},{"key":"B4","volume-title":"CAM2B-v2 [Software]","year":"2014"},{"key":"B5","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1044\/2019_AJA-19-00021","article-title":"A novel method for classifying hearing impairment in epidemiological studies of aging: the Wisconsin Age-Related hearing impairment classification scale","volume":"29","author":"Cruickshanks","year":"2020","journal-title":"Am. J. Audiol."},{"key":"B6","doi-asserted-by":"publisher","first-page":"2331216520914769","DOI":"10.1177\/2331216520914769","article-title":"Predicting speech perception in older listeners with sensorineural hearing loss using automatic speech recognition","volume":"24","author":"Fontan","year":"","journal-title":"Trends Hear."},{"key":"B7","doi-asserted-by":"crossref","first-page":"EL227","DOI":"10.1121\/10.0001866","article-title":"Using automatic speech recognition to optimize hearing-aid compression speed","volume":"148","author":"Fontan","year":"","journal-title":"J. Acoust. Soc. America"},{"key":"B8","doi-asserted-by":"publisher","first-page":"EL227","DOI":"10.1121\/10.0001866","article-title":"Improving hearing-aid gains based on automatic speech recognition","volume":"148","author":"Fontan","year":"","journal-title":"J. Acoust. Soc. Am."},{"key":"B9","volume-title":"Audiom\u00e9trie Vocale : Les \u00e9preuves d'intelligibilit\u00e9 et leurs Applications au Diagnostic, \u00e0 l'Expertise et \u00e0 la Correction Proth\u00e9tique des Surdit\u00e9s\u2014[Speech Audiometry: Speech-Intelligibility Tests and Their Application for the Diagnosis, Survey and Hearing-aid Rehabilitation of Hearing Losses]","author":"Fournier","year":"1951"},{"key":"B10","first-page":"885","article-title":"Corpus description of the ESTER evaluation campaign for the rich transcription of French broadcast news","volume-title":"Proceedings of the 5","author":"Galliano","year":"2006"},{"key":"B11","doi-asserted-by":"crossref","first-page":"2583","DOI":"10.21437\/Interspeech.2009-680","article-title":"The ESTER 2 evaluation campaign for the rich transcription of French radio broadcasts","volume-title":"INTERSPEECH 2009, 10","author":"Galliano","year":"2009"},{"key":"B12","volume-title":"Genetic Algorithms in Search, Optimization, and Machine Learning","author":"Goldberg","year":"1989"},{"key":"B13","first-page":"686","article-title":"Clarity-2021 challenges: machine learning challenges for advancing hearing aid processing","volume-title":"Proceedings of the Annual Conference of the International Speech Communication Association (INTERSPEECH)","author":"Graetzer","year":"2021"},{"key":"B14","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1044\/2021_AJA-20-00207","article-title":"Further evaluation and application of the Wisconsin Age-Related hearing impairment classification system","volume":"30","author":"Humes","year":"2021","journal-title":"Am. J. Audiol."},{"key":"B15","doi-asserted-by":"publisher","first-page":"198","DOI":"10.1044\/1058-0360(2003\/066)","article-title":"Effects of presentation mode and repeated familiarization on intelligibility of dysarthric speech","volume":"12","author":"Hustad","year":"2003","journal-title":"Am. J. Speech Lang. Pathol."},{"key":"B16","doi-asserted-by":"publisher","first-page":"e24","DOI":"10.4081\/audiores.2011.e24","article-title":"The NAL-NL2 prescription procedure","volume":"1","author":"Keidser","year":"2011","journal-title":"Audiol. Res."},{"key":"B17","first-page":"131","article-title":"Recent development of open-source speech recognition engine Julius","volume-title":"Proceedings of the 2009 Annual Summit and Conference of the Asia-Pacific Signal and Information Processing Association (APSIPA ASC 2009)","author":"Lee","year":"2009"},{"key":"B18","volume-title":"Cochlear Hearing Loss: Physiological, Psychological and Technical Issues","author":"Moore","year":"2008"},{"key":"B19","doi-asserted-by":"publisher","first-page":"360","DOI":"10.1121\/1.3436533","article-title":"Effect of spatial separation, extended bandwidth, and compression speed on intelligibility in a competing-speech task","volume":"128","author":"Moore","year":"","journal-title":"J. Acoust. Soc. Am."},{"key":"B20","doi-asserted-by":"publisher","first-page":"556","DOI":"10.1097\/AUD.0b013e31820b5f4c","article-title":"Determination of preferred parameters for multichannel compression using individually fitted simulated hearing aids and paired comparisons","volume":"32","author":"Moore","year":"2011","journal-title":"Ear Hear."},{"key":"B21","doi-asserted-by":"publisher","first-page":"2050","DOI":"10.1121\/1.407478","article-title":"Simulation of the effects of loudness recruitment and threshold elevation on the intelligibility of speech in quiet and in a background of speech","volume":"94","author":"Moore","year":"1993","journal-title":"J. Acoust. Soc. Am."},{"key":"B22","doi-asserted-by":"publisher","first-page":"216","DOI":"10.3109\/14992020903296746","article-title":"Development of a new method for deriving initial fittings for hearing aids with multi-channel compression: CAMEQ2-HF","volume":"49","author":"Moore","year":"","journal-title":"Int. J. Audiol."},{"key":"B23","doi-asserted-by":"publisher","first-page":"2331216516640486","DOI":"10.1177\/2331216516640486","article-title":"Preferred compression speed for speech and music and its relationship to sensitivity to temporal fine structure","volume":"20","author":"Moore","year":"2016","journal-title":"Trends Hear."},{"key":"B24","doi-asserted-by":"publisher","first-page":"603","DOI":"10.1121\/1.419733","article-title":"Simulation of the effect of threshold elevation and loudness recruitment combined with reduced frequency selectivity on the intelligibility of speech in noise","volume":"102","author":"Nejime","year":"1997","journal-title":"J. Acoust. Soc. Am."},{"key":"B25","volume-title":"R: A Language and Environment for Statistical Computing","year":"2021"},{"key":"B26","first-page":"22","article-title":"L'audiom\u00e9trie vocale en France: \u00e9tat des lieux [Speech audiometry in France: current clinical practices]","volume":"6","author":"Rembaud","year":"2017","journal-title":"Cahiers de l'Audition"},{"key":"B27","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1177\/108471380500900403","article-title":"The desired sensation level multistage input\/output algorithm","volume":"9","author":"Scollie","year":"2005","journal-title":"Trends Amplific."},{"key":"B28","doi-asserted-by":"publisher","first-page":"2331216519847413","DOI":"10.1177\/2331216519847413","article-title":"Perceptual effects of adjusting hearing-aid gain by means of a machine-learning approach based on individual user preference","volume":"23","author":"S\u00f8gaard Jensen","year":"2019","journal-title":"Trends Hear."},{"key":"B29","doi-asserted-by":"crossref","first-page":"456","DOI":"10.1121\/1.389839","article-title":"Effects of auditory fatigue on speech intelligibility and lexical decision in noise","volume":"74","author":"Sorin","year":"1983","journal-title":"J. Acoust. Soc. Am."},{"key":"B30","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1177\/108471380200600402","article-title":"Effects of compression on speech acoustics, intelligibility, and sound quality","volume":"6","author":"Souza","year":"2002","journal-title":"Trends Amplific."},{"key":"B31","doi-asserted-by":"publisher","first-page":"162","DOI":"10.1097\/00003446-199604000-00008","article-title":"Compression and its effect on the speech signal","volume":"17","author":"Verschuure","year":"1996","journal-title":"Ear Hear."},{"key":"B32","author":"Young","year":"1994","journal-title":"The HTK Hidden Markov Model Toolkit: Design and Philosophy"}],"updated-by":[{"DOI":"10.3389\/fnins.2022.1095750","type":"erratum","label":"Erratum","source":"publisher","updated":{"date-parts":[[2022,12,9]],"date-time":"2022-12-09T00:00:00Z","timestamp":1670544000000}}],"container-title":["Frontiers in Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnins.2022.779048\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,9]],"date-time":"2022-12-09T08:52:24Z","timestamp":1670575944000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnins.2022.779048\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,21]]},"references-count":32,"alternative-id":["10.3389\/fnins.2022.779048"],"URL":"https:\/\/doi.org\/10.3389\/fnins.2022.779048","relation":{},"ISSN":["1662-453X"],"issn-type":[{"value":"1662-453X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,2,21]]},"article-number":"779048"}}