Automatic speech recognition predicts speech intelligibility and comprehension for listeners with simulated age-related hearing loss

Purpose: To assess speech processing for listeners with simulated age-related hearing loss (ARHL) and to investigate whether the observed performance can be replicated using an Automatic Speech Recognition (ASR) system. The long-term goal of this research is to develop a system that will assist aud...

Full description

Bibliographic Details
Main Authors: Fontan, Lionel, Ferrané, Isabelle, Farinas, Jérôme, Pinquier, Julien, Tardieu, Julien, Magnen, Cynthia, Gaillard, Pascal, Aumont, Xavier, Füllgrabe, Christian
Format: Article
Published: American Speech-Language-Hearing Association 2017
Subjects:
Online Access:https://eprints.nottingham.ac.uk/44905/
_version_ 1848797024886980608
author Fontan, Lionel
Ferrané, Isabelle
Farinas, Jérôme
Pinquier, Julien
Tardieu, Julien
Magnen, Cynthia
Gaillard, Pascal
Aumont, Xavier
Füllgrabe, Christian
author_facet Fontan, Lionel
Ferrané, Isabelle
Farinas, Jérôme
Pinquier, Julien
Tardieu, Julien
Magnen, Cynthia
Gaillard, Pascal
Aumont, Xavier
Füllgrabe, Christian
author_sort Fontan, Lionel
building Nottingham Research Data Repository
collection Online Access
description Purpose: To assess speech processing for listeners with simulated age-related hearing loss (ARHL) and to investigate whether the observed performance can be replicated using an Automatic Speech Recognition (ASR) system. The long-term goal of this research is to develop a system that will assist audiologists/hearing-aid dispensers in the fine-tuning of hearing aids. Method: Sixty young normal-hearing participants listened to speech materials mimicking the perceptual consequences of ARHL at different levels of severity. Two intelligibility tests (repetition of words and sentences) and one comprehension test (responding to oral commands by moving virtual objects) were administered. Several language models were developed and used by the ASR system in order to fit human performances. Results: Strong significant positive correlations were observed between human and ASR scores, with coefficients up to .99. However, the spectral smearing used to simulate losses in frequency selectivity caused larger declines in ASR performance than in human performance. Conclusion: Both intelligibility and comprehension scores for listeners with simulated ARHL are highly correlated with the performances of an ASR-based system. In the future, it needs to be determined if the ASR system is similarly successful in predicting speech processing in noise and by older people with ARHL.
first_indexed 2025-11-14T19:57:18Z
format Article
id nottingham-44905
institution University of Nottingham Malaysia Campus
institution_category Local University
last_indexed 2025-11-14T19:57:18Z
publishDate 2017
publisher American Speech-Language-Hearing Association
recordtype eprints
repository_type Digital Repository
spelling nottingham-449052020-05-04T19:00:07Z https://eprints.nottingham.ac.uk/44905/ Automatic speech recognition predicts speech intelligibility and comprehension for listeners with simulated age-related hearing loss Fontan, Lionel Ferrané, Isabelle Farinas, Jérôme Pinquier, Julien Tardieu, Julien Magnen, Cynthia Gaillard, Pascal Aumont, Xavier Füllgrabe, Christian Purpose: To assess speech processing for listeners with simulated age-related hearing loss (ARHL) and to investigate whether the observed performance can be replicated using an Automatic Speech Recognition (ASR) system. The long-term goal of this research is to develop a system that will assist audiologists/hearing-aid dispensers in the fine-tuning of hearing aids. Method: Sixty young normal-hearing participants listened to speech materials mimicking the perceptual consequences of ARHL at different levels of severity. Two intelligibility tests (repetition of words and sentences) and one comprehension test (responding to oral commands by moving virtual objects) were administered. Several language models were developed and used by the ASR system in order to fit human performances. Results: Strong significant positive correlations were observed between human and ASR scores, with coefficients up to .99. However, the spectral smearing used to simulate losses in frequency selectivity caused larger declines in ASR performance than in human performance. Conclusion: Both intelligibility and comprehension scores for listeners with simulated ARHL are highly correlated with the performances of an ASR-based system. In the future, it needs to be determined if the ASR system is similarly successful in predicting speech processing in noise and by older people with ARHL. American Speech-Language-Hearing Association 2017-08-11 Article PeerReviewed Fontan, Lionel, Ferrané, Isabelle, Farinas, Jérôme, Pinquier, Julien, Tardieu, Julien, Magnen, Cynthia, Gaillard, Pascal, Aumont, Xavier and Füllgrabe, Christian (2017) Automatic speech recognition predicts speech intelligibility and comprehension for listeners with simulated age-related hearing loss. Journal of Speech, Language, and Hearing Research . pp. 1-12. ISSN 1558-9102 Hearing loss Speech recognition Amplification or hearing aids Assessment Speech perception http://jslhr.pubs.asha.org/article.aspx?articleid=2648888 doi:10.1044/2017_JSLHR-S-16-0269 doi:10.1044/2017_JSLHR-S-16-0269
spellingShingle Hearing loss
Speech recognition
Amplification or hearing aids
Assessment
Speech perception
Fontan, Lionel
Ferrané, Isabelle
Farinas, Jérôme
Pinquier, Julien
Tardieu, Julien
Magnen, Cynthia
Gaillard, Pascal
Aumont, Xavier
Füllgrabe, Christian
Automatic speech recognition predicts speech intelligibility and comprehension for listeners with simulated age-related hearing loss
title Automatic speech recognition predicts speech intelligibility and comprehension for listeners with simulated age-related hearing loss
title_full Automatic speech recognition predicts speech intelligibility and comprehension for listeners with simulated age-related hearing loss
title_fullStr Automatic speech recognition predicts speech intelligibility and comprehension for listeners with simulated age-related hearing loss
title_full_unstemmed Automatic speech recognition predicts speech intelligibility and comprehension for listeners with simulated age-related hearing loss
title_short Automatic speech recognition predicts speech intelligibility and comprehension for listeners with simulated age-related hearing loss
title_sort automatic speech recognition predicts speech intelligibility and comprehension for listeners with simulated age-related hearing loss
topic Hearing loss
Speech recognition
Amplification or hearing aids
Assessment
Speech perception
url https://eprints.nottingham.ac.uk/44905/
https://eprints.nottingham.ac.uk/44905/
https://eprints.nottingham.ac.uk/44905/