OATAO - Open Archive Toulouse Archive Ouverte Open Access Week

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

Fontan, Lionel and Ferrané, Isabelle and Farinas, Jérôme and Pinquier, Julien and Tardieu, Julien and Magnen, Cynthia and Gaillard, Pascal and Aumont, Xavier and Füllgrabe, Christian Automatic speech recognition predicts speech intelligibility and comprehension for listeners with simulated age-related hearing loss. (2017) Journal of Speech, Language and Hearing Research, 60. 2393-2404. ISSN 1092-4388

[img]
Preview
(Document in English)

PDF (Author's version) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
739kB

Official URL: http://dx.doi.org/10.1044/2017_JSLHR-S-16-0269

Abstract

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 corresponding to ages from 60 to 110 years. Two intelligibility tests (repetition of words and sentences) and one comprehension test (responding to oral commands by moving virtual objects on a computer screen) 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.

Item Type:Article
Additional Information:Published under the terms of the Creative Commons Attribution License, the original PDF can be found at Journal of Speech, Language and Hearing Research (ISSN 1092-4388) website : https://jslhr.pubs.asha.org/article.aspx?articleid=2648888
Audience (journal):International peer-reviewed journal
Uncontrolled Keywords:
Institution:French research institutions > Centre National de la Recherche Scientifique - CNRS (FRANCE)
Université de Toulouse > Institut National Polytechnique de Toulouse - INPT (FRANCE)
Université de Toulouse > Université Toulouse III - Paul Sabatier - UPS (FRANCE)
Université de Toulouse > Université Toulouse - Jean Jaurès - UT2J (FRANCE)
Université de Toulouse > Université Toulouse 1 Capitole - UT1 (FRANCE)
Other partners > University of Nottingham (UNITED KINGDOM)
Other partners > Archean Technologies (FRANCE)
Laboratory name:
Statistics:download
Deposited By: IRIT IRIT
Deposited On:14 May 2018 14:54

Repository Staff Only: item control page