OPRA-RS: A Hearing-Aid Fitting Method Based on Automatic Speech Recognition and Random Search
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 intelligib...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2022-02-01
|
Series: | Frontiers in Neuroscience |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fnins.2022.779048/full |
_version_ | 1811205247337496576 |
---|---|
author | Libio Gonçalves Braz Lionel Fontan Julien Pinquier Michael A. Stone Christian Füllgrabe |
author_facet | Libio Gonçalves Braz Lionel Fontan Julien Pinquier Michael A. Stone Christian Füllgrabe |
author_sort | Libio Gonçalves Braz |
collection | DOAJ |
description | 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 “objective 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. |
first_indexed | 2024-04-12T03:27:26Z |
format | Article |
id | doaj.art-acbe6b60200142d882680d7b5d749f90 |
institution | Directory Open Access Journal |
issn | 1662-453X |
language | English |
last_indexed | 2024-04-12T03:27:26Z |
publishDate | 2022-02-01 |
publisher | Frontiers Media S.A. |
record_format | Article |
series | Frontiers in Neuroscience |
spelling | doaj.art-acbe6b60200142d882680d7b5d749f902022-12-22T03:49:39ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2022-02-011610.3389/fnins.2022.779048779048OPRA-RS: A Hearing-Aid Fitting Method Based on Automatic Speech Recognition and Random SearchLibio Gonçalves Braz0Lionel Fontan1Julien Pinquier2Michael A. Stone3Christian Füllgrabe4IRIT, CNRS, Université Paul Sabatier, Toulouse, FranceArchean LABS, Montauban, FranceIRIT, CNRS, Université Paul Sabatier, Toulouse, FranceManchester Centre for Audiology and Deafness, School of Health Sciences, University of Manchester, Manchester, United KingdomSchool of Sport, Exercise and Health Sciences, Loughborough University, Loughborough, United KingdomHearing-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 “objective 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.https://www.frontiersin.org/articles/10.3389/fnins.2022.779048/fullrandom search (RS)automatic speech recognition (ASR)hearing aids (HAs)prescription ruleage-related hearing loss (ARHL)insertion gains |
spellingShingle | Libio Gonçalves Braz Lionel Fontan Julien Pinquier Michael A. Stone Christian Füllgrabe OPRA-RS: A Hearing-Aid Fitting Method Based on Automatic Speech Recognition and Random Search Frontiers in Neuroscience random search (RS) automatic speech recognition (ASR) hearing aids (HAs) prescription rule age-related hearing loss (ARHL) insertion gains |
title | OPRA-RS: A Hearing-Aid Fitting Method Based on Automatic Speech Recognition and Random Search |
title_full | OPRA-RS: A Hearing-Aid Fitting Method Based on Automatic Speech Recognition and Random Search |
title_fullStr | OPRA-RS: A Hearing-Aid Fitting Method Based on Automatic Speech Recognition and Random Search |
title_full_unstemmed | OPRA-RS: A Hearing-Aid Fitting Method Based on Automatic Speech Recognition and Random Search |
title_short | OPRA-RS: A Hearing-Aid Fitting Method Based on Automatic Speech Recognition and Random Search |
title_sort | opra rs a hearing aid fitting method based on automatic speech recognition and random search |
topic | random search (RS) automatic speech recognition (ASR) hearing aids (HAs) prescription rule age-related hearing loss (ARHL) insertion gains |
url | https://www.frontiersin.org/articles/10.3389/fnins.2022.779048/full |
work_keys_str_mv | AT libiogoncalvesbraz oprarsahearingaidfittingmethodbasedonautomaticspeechrecognitionandrandomsearch AT lionelfontan oprarsahearingaidfittingmethodbasedonautomaticspeechrecognitionandrandomsearch AT julienpinquier oprarsahearingaidfittingmethodbasedonautomaticspeechrecognitionandrandomsearch AT michaelastone oprarsahearingaidfittingmethodbasedonautomaticspeechrecognitionandrandomsearch AT christianfullgrabe oprarsahearingaidfittingmethodbasedonautomaticspeechrecognitionandrandomsearch |