Skip to content

Phonological Posterior Probabilities as Interpretable Markers of Articulatory Impairment in Motor Speech Disorders.

Oct 2026 · Journal of Speech, Language and Hearing Research · Vol 69, pp. 1-20 · 0 citations · 50 references
Medicine

TL;DR

Phoneme-level posterior probabilities serve as interpretable, segment-specific indicators of articulatory impairment in MSDs, making them promising tools for augmenting traditional perceptual speech assessments.

Abstract

Purpose

This study examined whether phoneme-level posterior probabilities generated by an articulatory-informed deep learning model (Phonet) can serve as interpretable and sensitive markers of articulatory impairment in motor speech disorders (MSDs). The goal was to determine whether these features distinguish individuals with and without MSDs and reflect varying severity levels of articulatory impairment.

Method

A total of 676 participants (199 with MSDs, 477 without MSDs) completed a remotely captured word repetition task. Speech recordings were phonetically aligned, and posterior probabilities were extracted using a retrained version of the Phonet model, which estimates frame-level probabilities for 23 phonological classes. Segment-level posterior values were computed and compared across groups and severity levels using linear mixed-effects regression models.

Results

Posterior probabilities were significantly reduced in the MSD group across all phoneme types. Within the MSD group, posterior probabilities decreased progressively with greater clinical severity, as measured by both perceptual sound distortion ratings and a cumulative articulation error score. Segment-specific analyses revealed systematic differences across phoneme classes, indicating that posterior probabilities capture distinct patterns of articulatory degradation associated with motor speech impairment.

Conclusions

Phoneme-level posterior probabilities serve as interpretable, segment-specific indicators of articulatory impairment in MSDs. These features differentiate clinical status and reflect gradations of severity, making them promising tools for augmenting traditional perceptual speech assessments. Their linguistic transparency and scalability support future clinical applications in diagnosis, monitoring, and targeted intervention.

View source

Similar papers

Open access Oct 2026

Individual differences in motor and auditory activation in second language speech learning: Roles of domain-general auditory processing.

While existing models emphasize the critical roles of auditory and motor systems in speech perception, it remains unclear how individual learners differentially rely on these systems and how their relative weighting relates to language learning. This study investigates the neural mechanisms through which individual dif...

Kazuya Saito-van Poeteren, A. Tierney, Kotaro Takizawa et al. · 1 citation
Open access Sep 2026

Acoustic Features of Sustained Phonation for Schizophrenia Classification: A Feasibility Study

Voice and speech are increasingly studied as indicators of mental health, but the acoustic features of sustained phonation in schizophrenia remain underexplored. This feasibility study examined whether a 500 ms sustained vowel /a/ contains meaningful information for distinguishing patients with schizophrenia from healt...

L. Jelić, K. Jambrošić, Vinko Lešić et al. · 0 citations
Open access Nov 2026

Phonologically Similar, High-Density Targets to Improve Intelligibility: A Single-Case Study in a Cypriot-Greek–Speaking Child with Consistent Phonological Disorder

This study examined whether training with phonologically similar, high–neighborhood-density word cohorts promotes expressive phonological gains in a 4-year-old bidialectal Cypriot-Greek–speaking child with a consistent phonological disorder. Using a single-case design with baseline, intervention, post-test, and 1-mon...

Elma Filippou, Theodora Papastefanou, Kakia Petinou · 0 citations
Open access Sep 2026

Evaluating Phonological Knowledge in Foundational Speech Models

Speech foundation models are primarily evaluated with task-level metrics, which do not establish whether language-specific phonological patterns are encoded or faithfully reproduced. This dissertation asks what evidence is required to distinguish recoverable acoustic or distributional information from phonological gene...

S. Barman · 0 citations
Oct 2026

Altered frontal and dorsal hemodynamic engagement during mandarin aspiration processing in post-stroke aphasia: an fNIRS study.

Auditory and speech-perception difficulties are common in post-stroke aphasia (PSA), but cortical responses during passive listening to Mandarin speech remain underexplored. Seventeen Mandarin-speaking individuals with PSA and 18 matched healthy controls listened to auditory oddball blocks containing /ba/ standards and...

Juan Cheng, Tai-Lin Ren, Yi-Zhen Liu et al. · 0 citations
Open access Sep 2026

Impaired cortical encoding of prosodic prominence in single multisyllabic words for adults with dyslexia

Developmental dyslexia is associated with impaired cortical tracking of continuous speech and difficulties in perceiving within-word prosodic structure in children and adults. For adults and continuous speech, both low-frequency delta- and theta-band impairments and high-frequency gamma- and beta-band differences are f...

Mahmoud Keshavarzi, Brian C. J. Moore, U. Goswami · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.