Automated Assessment of Word- and Sentence-Level Speech Intelligibility in Developmental Motor Speech Disorders: A Cross-Linguistic Investigation

<b>Background/Objectives</b>: Accurate assessment of speech intelligibility is necessary for individuals with motor speech disorders. Transcription or scaled rating methods by naïve listeners are the most reliable tasks for these purposes; however, they are often resource-intensive and t...

Full description

Saved in:
Bibliographic Details
Main Authors: Micalle Carl, Michal Icht
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Diagnostics
Subjects:
Online Access:https://www.mdpi.com/2075-4418/15/15/1892
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849239865328140288
author Micalle Carl
Michal Icht
author_facet Micalle Carl
Michal Icht
author_sort Micalle Carl
collection DOAJ
description <b>Background/Objectives</b>: Accurate assessment of speech intelligibility is necessary for individuals with motor speech disorders. Transcription or scaled rating methods by naïve listeners are the most reliable tasks for these purposes; however, they are often resource-intensive and time-consuming within clinical contexts. Automatic speech recognition (ASR) systems, which transcribe speech into text, have been increasingly utilized for assessing speech intelligibility. This study investigates the feasibility of using an open-source ASR system to assess speech intelligibility in Hebrew and English speakers with Down syndrome (DS). <b>Methods</b>: Recordings from 65 Hebrew- and English-speaking participants were included: 33 speakers with DS and 32 typically developing (TD) peers. Speech samples (words, sentences) were transcribed using Whisper (OpenAI) and by naïve listeners. The proportion of agreement between ASR transcriptions and those of naïve listeners was compared across speaker groups (TD, DS) and languages (Hebrew, English) for word-level data. Further comparisons for Hebrew speakers were conducted across speaker groups and stimuli (words, sentences). <b>Results</b>: The strength of the correlation between listener and ASR transcription scores varied across languages, and was higher for English (<i>r</i> = 0.98) than for Hebrew (<i>r</i> = 0.81) for speakers with DS. A higher proportion of listener–ASR agreement was demonstrated for TD speakers, as compared to those with DS (0.94 vs. 0.74, respectively), and for English, in comparison to Hebrew speakers (0.91 for English DS speakers vs. 0.74 for Hebrew DS speakers). Listener–ASR agreement for single words was consistently higher than for sentences among Hebrew speakers. Speakers’ intelligibility influenced word-level agreement among Hebrew- but not English-speaking participants with DS. <b>Conclusions</b>: ASR performance for English closely approximated that of naïve listeners, suggesting potential near-future clinical applicability within single-word intelligibility assessment. In contrast, a lower proportion of agreement between human listeners and ASR for Hebrew speech indicates that broader clinical implementation may require further training of ASR models in this language.
format Article
id doaj-art-3087c3cb905844df97cfdba1a8dc5f67
institution Kabale University
issn 2075-4418
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Diagnostics
spelling doaj-art-3087c3cb905844df97cfdba1a8dc5f672025-08-20T04:00:49ZengMDPI AGDiagnostics2075-44182025-07-011515189210.3390/diagnostics15151892Automated Assessment of Word- and Sentence-Level Speech Intelligibility in Developmental Motor Speech Disorders: A Cross-Linguistic InvestigationMicalle Carl0Michal Icht1Department of Communication Disorders, Ariel University, Ariel 40700, IsraelDepartment of Communication Disorders, Ariel University, Ariel 40700, Israel<b>Background/Objectives</b>: Accurate assessment of speech intelligibility is necessary for individuals with motor speech disorders. Transcription or scaled rating methods by naïve listeners are the most reliable tasks for these purposes; however, they are often resource-intensive and time-consuming within clinical contexts. Automatic speech recognition (ASR) systems, which transcribe speech into text, have been increasingly utilized for assessing speech intelligibility. This study investigates the feasibility of using an open-source ASR system to assess speech intelligibility in Hebrew and English speakers with Down syndrome (DS). <b>Methods</b>: Recordings from 65 Hebrew- and English-speaking participants were included: 33 speakers with DS and 32 typically developing (TD) peers. Speech samples (words, sentences) were transcribed using Whisper (OpenAI) and by naïve listeners. The proportion of agreement between ASR transcriptions and those of naïve listeners was compared across speaker groups (TD, DS) and languages (Hebrew, English) for word-level data. Further comparisons for Hebrew speakers were conducted across speaker groups and stimuli (words, sentences). <b>Results</b>: The strength of the correlation between listener and ASR transcription scores varied across languages, and was higher for English (<i>r</i> = 0.98) than for Hebrew (<i>r</i> = 0.81) for speakers with DS. A higher proportion of listener–ASR agreement was demonstrated for TD speakers, as compared to those with DS (0.94 vs. 0.74, respectively), and for English, in comparison to Hebrew speakers (0.91 for English DS speakers vs. 0.74 for Hebrew DS speakers). Listener–ASR agreement for single words was consistently higher than for sentences among Hebrew speakers. Speakers’ intelligibility influenced word-level agreement among Hebrew- but not English-speaking participants with DS. <b>Conclusions</b>: ASR performance for English closely approximated that of naïve listeners, suggesting potential near-future clinical applicability within single-word intelligibility assessment. In contrast, a lower proportion of agreement between human listeners and ASR for Hebrew speech indicates that broader clinical implementation may require further training of ASR models in this language.https://www.mdpi.com/2075-4418/15/15/1892speech intelligibilityautomatic speech recognition (ASR)down syndromemotor speech disorderscross-linguistic assessment
spellingShingle Micalle Carl
Michal Icht
Automated Assessment of Word- and Sentence-Level Speech Intelligibility in Developmental Motor Speech Disorders: A Cross-Linguistic Investigation
Diagnostics
speech intelligibility
automatic speech recognition (ASR)
down syndrome
motor speech disorders
cross-linguistic assessment
title Automated Assessment of Word- and Sentence-Level Speech Intelligibility in Developmental Motor Speech Disorders: A Cross-Linguistic Investigation
title_full Automated Assessment of Word- and Sentence-Level Speech Intelligibility in Developmental Motor Speech Disorders: A Cross-Linguistic Investigation
title_fullStr Automated Assessment of Word- and Sentence-Level Speech Intelligibility in Developmental Motor Speech Disorders: A Cross-Linguistic Investigation
title_full_unstemmed Automated Assessment of Word- and Sentence-Level Speech Intelligibility in Developmental Motor Speech Disorders: A Cross-Linguistic Investigation
title_short Automated Assessment of Word- and Sentence-Level Speech Intelligibility in Developmental Motor Speech Disorders: A Cross-Linguistic Investigation
title_sort automated assessment of word and sentence level speech intelligibility in developmental motor speech disorders a cross linguistic investigation
topic speech intelligibility
automatic speech recognition (ASR)
down syndrome
motor speech disorders
cross-linguistic assessment
url https://www.mdpi.com/2075-4418/15/15/1892
work_keys_str_mv AT micallecarl automatedassessmentofwordandsentencelevelspeechintelligibilityindevelopmentalmotorspeechdisordersacrosslinguisticinvestigation
AT michalicht automatedassessmentofwordandsentencelevelspeechintelligibilityindevelopmentalmotorspeechdisordersacrosslinguisticinvestigation