Improving hearing-aid gains based on automatic speech recognition

Lionel Fontan; Maxime Le Coz; Charlotte Azzopardi; Michael Stone; Christian Füllgrabe

doi:10.1121/10.0001866

Improving hearing-aid gains based on automatic speech recognition

Lionel Fontan, Maxime Le Coz, Charlotte Azzopardi, Michael Stone, Christian Füllgrabe

Division of Human Communication, Development & Hearing (L5)

Research output: Contribution to journal › Letter › peer-review

93 Downloads (Pure)

Abstract

This study provides proof of concept that automatic speech recognition (ASR)
can be used to improve hearing aid (HA) fitting. A signal-processing chain consisting of a HA simulator, a hearing-loss simulator, and an ASR system normalizing the intensity of input signals was used to find HA-gain functions yielding the highest ASR intelligibility scores for individual audiometric profiles of 24 listeners with age-related hearing loss.
Significantly higher aided speech intelligibility scores and subjective ratings of speech pleasantness were observed when the participants were fitted with ASR-established gains than when fitted with the gains recommended by the CAM2 fitting rule.

Original language	English
Pages (from-to)	EL227-EL233
Number of pages	7
Journal	The Journal of the Acoustical Society of America
Volume	148
Issue number	3
DOIs	https://doi.org/10.1121/10.0001866
Publication status	Published - 8 Sep 2020

Keywords

hearing aids
automatic speech recognition
fitting rule

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1121/10.0001866

FontanLeCozAzzopardiStoneFullgrabe_HAGainsBasedOnAutomSpeechRecog_JASA_EL2272020Final published version, 1.4 MBLicence: Unspecified

Manchester Centre for Audiology and Deafness (ManCAD)
Munro, K., Millman, R., Lamb, W., Dawes, P., Plack, C., Stone, M., Kluk-De Kort, K., Moore, D., Morton, C., Prendergast, G., Couth, S., Schlittenlacher, J., Chilton, H., Visram, A., Dillon, H., Guest, H., Heinrich, A., Jackson, I., Littlejohn, J., Jones, L., Lough, M., Morgan, R., Perugia, E., Roughley, A., Short, A., Whiston, H., Wright, C., Saunders, G. & Kelly, C.
Project: Research

1 Article

OPRA-RS: A Hearing-Aid Fitting Method Based on Automatic Speech Recognition and Random Search
Goncalves Braz, L., Fontan, L., Pinquier, J., Stone, M. & Fullgrabe, C., 21 Feb 2022, In: Frontiers in Neuroscience.
Research output: Contribution to journal › Article › peer-review

Open Access

Cite this

@article{d6449296418f416f8b295ad4b4f960d4,

title = "Improving hearing-aid gains based on automatic speech recognition",

abstract = "This study provides proof of concept that automatic speech recognition (ASR)can be used to improve hearing aid (HA) fitting. A signal-processing chain consisting of a HA simulator, a hearing-loss simulator, and an ASR system normalizing the intensity of input signals was used to find HA-gain functions yielding the highest ASR intelligibility scores for individual audiometric profiles of 24 listeners with age-related hearing loss.Significantly higher aided speech intelligibility scores and subjective ratings of speech pleasantness were observed when the participants were fitted with ASR-established gains than when fitted with the gains recommended by the CAM2 fitting rule.",

keywords = "hearing aids, automatic speech recognition, fitting rule",

author = "Lionel Fontan and {Le Coz}, Maxime and Charlotte Azzopardi and Michael Stone and Christian F{\"u}llgrabe",

year = "2020",

month = sep,

day = "8",

doi = "10.1121/10.0001866",

language = "English",

volume = "148",

pages = "EL227--EL233",

journal = "Acoustical Society of America. Journal",

issn = "0001-4966",

publisher = "Acoustical Society of America",

number = "3",

}

TY - JOUR

T1 - Improving hearing-aid gains based on automatic speech recognition

AU - Fontan, Lionel

AU - Le Coz, Maxime

AU - Azzopardi, Charlotte

AU - Stone, Michael

AU - Füllgrabe, Christian

PY - 2020/9/8

Y1 - 2020/9/8

N2 - This study provides proof of concept that automatic speech recognition (ASR)can be used to improve hearing aid (HA) fitting. A signal-processing chain consisting of a HA simulator, a hearing-loss simulator, and an ASR system normalizing the intensity of input signals was used to find HA-gain functions yielding the highest ASR intelligibility scores for individual audiometric profiles of 24 listeners with age-related hearing loss.Significantly higher aided speech intelligibility scores and subjective ratings of speech pleasantness were observed when the participants were fitted with ASR-established gains than when fitted with the gains recommended by the CAM2 fitting rule.

AB - This study provides proof of concept that automatic speech recognition (ASR)can be used to improve hearing aid (HA) fitting. A signal-processing chain consisting of a HA simulator, a hearing-loss simulator, and an ASR system normalizing the intensity of input signals was used to find HA-gain functions yielding the highest ASR intelligibility scores for individual audiometric profiles of 24 listeners with age-related hearing loss.Significantly higher aided speech intelligibility scores and subjective ratings of speech pleasantness were observed when the participants were fitted with ASR-established gains than when fitted with the gains recommended by the CAM2 fitting rule.

KW - hearing aids

KW - automatic speech recognition

KW - fitting rule

U2 - 10.1121/10.0001866

DO - 10.1121/10.0001866

M3 - Letter

VL - 148

SP - EL227-EL233

JO - Acoustical Society of America. Journal

JF - Acoustical Society of America. Journal

SN - 0001-4966

IS - 3

ER -

Improving hearing-aid gains based on automatic speech recognition

Abstract

Keywords

UN SDGs

Access to Document

Fingerprint

Projects

Manchester Centre for Audiology and Deafness (ManCAD)

Research output

OPRA-RS: A Hearing-Aid Fitting Method Based on Automatic Speech Recognition and Random Search

Cite this