Automatic development of speech-in-noise hearing tests using machine learning

Abstract Understanding speech in noisy environments is a primary challenge for individuals with hearing loss, affecting daily communication and quality of life. Traditional speech-in-noise tests are essential for screening and diagnosing hearing loss but are resource-intensive to develop, making the...

Full description

Saved in:
Bibliographic Details
Main Authors: Sigrid Polspoel, David R. Moore, De Wet Swanepoel, Sophia E. Kramer, Cas Smits
Format: Article
Language:English
Published: Nature Portfolio 2025-04-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-96312-z
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850146325126971392
author Sigrid Polspoel
David R. Moore
De Wet Swanepoel
Sophia E. Kramer
Cas Smits
author_facet Sigrid Polspoel
David R. Moore
De Wet Swanepoel
Sophia E. Kramer
Cas Smits
author_sort Sigrid Polspoel
collection DOAJ
description Abstract Understanding speech in noisy environments is a primary challenge for individuals with hearing loss, affecting daily communication and quality of life. Traditional speech-in-noise tests are essential for screening and diagnosing hearing loss but are resource-intensive to develop, making them less accessible in low and middle-income countries. This study introduces an artificial intelligence-based approach to automate the development of these tests. By leveraging text-to-speech and automatic speech recognition (ASR) technologies, the cost, time, and resources required for high-quality speech-in-noise testing could be reduced. The procedure, named “Aladdin” (Automatic LAnguage-independent Development of the digits-in-noise test), creates digits-in-noise (DIN) hearing tests through synthetic speech material and uses ASR-based level corrections to perceptually equalize the digits. Traditional DIN tests were compared with newly developed Dutch and English Aladdin tests in listeners with normal hearing and hearing loss. Aladdin tests showed 84% specificity and 100% sensitivity, similar to the reference DIN tests (87% and 100%). Aladdin provides a universal guideline for developing DIN tests across languages, addressing the challenge of comparing test results across variants. Aladdin’s approach represents a significant advancement in test development and offers an efficient enhancement to global screening and treatment for hearing loss.
format Article
id doaj-art-ce2ea97d136f44a6a3a1603b6174502c
institution OA Journals
issn 2045-2322
language English
publishDate 2025-04-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-ce2ea97d136f44a6a3a1603b6174502c2025-08-20T02:27:53ZengNature PortfolioScientific Reports2045-23222025-04-0115112010.1038/s41598-025-96312-zAutomatic development of speech-in-noise hearing tests using machine learningSigrid Polspoel0David R. Moore1De Wet Swanepoel2Sophia E. Kramer3Cas Smits4Otolaryngology-Head and Neck Surgery, Section Ear and Hearing, Amsterdam UMC location Vrije Universiteit AmsterdamDivision of Patient Services Research, Cincinnati Children’s Hospital Medical Center, and Department of Pediatrics, University of CincinnatiDepartment of Speech-Language Pathology and Audiology, University of PretoriaOtolaryngology-Head and Neck Surgery, Section Ear and Hearing, Amsterdam UMC location Vrije Universiteit AmsterdamAmsterdam Public Health research institute, Quality of CareAbstract Understanding speech in noisy environments is a primary challenge for individuals with hearing loss, affecting daily communication and quality of life. Traditional speech-in-noise tests are essential for screening and diagnosing hearing loss but are resource-intensive to develop, making them less accessible in low and middle-income countries. This study introduces an artificial intelligence-based approach to automate the development of these tests. By leveraging text-to-speech and automatic speech recognition (ASR) technologies, the cost, time, and resources required for high-quality speech-in-noise testing could be reduced. The procedure, named “Aladdin” (Automatic LAnguage-independent Development of the digits-in-noise test), creates digits-in-noise (DIN) hearing tests through synthetic speech material and uses ASR-based level corrections to perceptually equalize the digits. Traditional DIN tests were compared with newly developed Dutch and English Aladdin tests in listeners with normal hearing and hearing loss. Aladdin tests showed 84% specificity and 100% sensitivity, similar to the reference DIN tests (87% and 100%). Aladdin provides a universal guideline for developing DIN tests across languages, addressing the challenge of comparing test results across variants. Aladdin’s approach represents a significant advancement in test development and offers an efficient enhancement to global screening and treatment for hearing loss.https://doi.org/10.1038/s41598-025-96312-zArtificial intelligence (AI)Synthetic speechText-to-speech (TTS)Automatic speech recognition (ASR)AladdinDigits-in-noise test
spellingShingle Sigrid Polspoel
David R. Moore
De Wet Swanepoel
Sophia E. Kramer
Cas Smits
Automatic development of speech-in-noise hearing tests using machine learning
Scientific Reports
Artificial intelligence (AI)
Synthetic speech
Text-to-speech (TTS)
Automatic speech recognition (ASR)
Aladdin
Digits-in-noise test
title Automatic development of speech-in-noise hearing tests using machine learning
title_full Automatic development of speech-in-noise hearing tests using machine learning
title_fullStr Automatic development of speech-in-noise hearing tests using machine learning
title_full_unstemmed Automatic development of speech-in-noise hearing tests using machine learning
title_short Automatic development of speech-in-noise hearing tests using machine learning
title_sort automatic development of speech in noise hearing tests using machine learning
topic Artificial intelligence (AI)
Synthetic speech
Text-to-speech (TTS)
Automatic speech recognition (ASR)
Aladdin
Digits-in-noise test
url https://doi.org/10.1038/s41598-025-96312-z
work_keys_str_mv AT sigridpolspoel automaticdevelopmentofspeechinnoisehearingtestsusingmachinelearning
AT davidrmoore automaticdevelopmentofspeechinnoisehearingtestsusingmachinelearning
AT dewetswanepoel automaticdevelopmentofspeechinnoisehearingtestsusingmachinelearning
AT sophiaekramer automaticdevelopmentofspeechinnoisehearingtestsusingmachinelearning
AT cassmits automaticdevelopmentofspeechinnoisehearingtestsusingmachinelearning