BackgroundDigital speech analysis affords robust markers of Parkinson's disease (PD). However, most studies target late-onset PD (LOPD), neglecting early-onset PD (EOPD) -an increasingly prevalent subtype. This proof-of-concept study tackles such gap.MethodsWe used machine learning to discriminate persons with EOPD (with symptom onset before age 50) and LOPD (with symptom onset after age 50) from healthy controls (HCs) through prosodic and articulatory features from natural speech.ResultsMaximal classification between patients and HCs was afforded by combined prosodic and articulation features in LOPD (AUC = 0.90) and by articulation alone in EOPD (AUC = 0.79), with chance-level discrimination between patient groups (AUC = 0.55). Motor severity (MDS-UPDRS-III) scores predicted by these features correlated with actual motor severity scores in both LOPD (r = 0.52, p < 0.001) and EOPD (r = 0.27, p < 0.001).ConclusionsDigital speech markers offer markers of PD irrespective of age of onset.

This study was performed to develop and validate the quality of life scale for postpalatoplasty and noncleft FAD (Functional Articulation Disorder) patients and to survey their quality of life (QoL) status. A mixed-methods scale development process yielded a 20-item instrument. Psychometric properties were evaluated in 128 children (41 postpalatoplasty FAD, 87 noncleft FAD). Speech clarity was assessed in a subset (n=38). The scale demonstrated excellent reliability (Cronbach α=0.963) and validity. Postpalatoplasty FAD patients reported significantly poorer QoL than noncleft FAD patients, with a greater impact on females. Parent-child agreement was lower on social perception items. Objective speech clarity was negatively correlated with QoL scores (P<0.05). This valid scale fills an important assessment gap. Results confirm the substantial psychosocial burden of FAD, indicating a need for targeted psychosocial support alongside speech therapy.

Speech production difficulties in autism spectrum disorder (ASD) are heterogeneous and are not uniformly characterized by articulatory impairment across the spectrum. However, some autistic subgroups, particularly minimally verbal children, children with low expressive-language ability, and those with suspected co-occurring speech-motor difficulties, may show atypical vowel-acoustic patterns. Because vowel production can be quantified through measures such as formant frequencies, vowel-space area, duration, and variability, these parameters may offer useful objective information for characterizing speech impairment and informing rehabilitation planning in selected phenotypes. This narrative review critically examined the literature on vowel-acoustic characteristics in autistic children and their possible relevance to rehabilitation-oriented systems. Structured searches of PubMed, Scopus, and Web of Science were conducted for studies published up to September 2025. Evidence suggests that some autistic subgroups may exhibit reduced vowel distinctiveness, greater acoustic variability, and atypical temporal or dynamic speech features, although findings are heterogeneous and do not support a single uniform acoustic profile across ASD. Direct intervention evidence remains limited. Most rehabilitation-related studies are small, exploratory investigations, and the available literature is concentrated largely around Auditory-Motor Mapping Training (AMMT), an indirectly relevant speech-motor intervention that reports vowel-related outcomes but does not directly target vowel-acoustic parameters in isolation.Overall, vowel-acoustic measures are better regarded as candidate quantitative tools for subgroup characterization, monitoring, and rehabilitation planning rather than as universal biomarkers across ASD. Their translational potential is promising but remains insufficiently validated, requiring stronger longitudinal, mechanistic, and intervention research before broad clinical application can be justified.

Children born with cleft palate, with or without cleft lip (CP ± L), are at high risk for speech and resonance disorders that can significantly impact communication and quality of life. Causes of cleft-related speech disorders include velopharyngeal insufficiency, malocclusion, dental anomalies, and airway obstruction. Accurate differential diagnosis is critical, as mismanagement can result in unnecessary surgery or ineffective therapy. Nonetheless, many children do not receive specialist evaluation or targeted intervention. Optimal outcomes require coordinated multidisciplinary care, with speech-language pathologists (SLPs) playing a central role in the assessment and treatment of feeding, articulation, resonance, and velopharyngeal function. However, a global shortage of trained SLPs has created major barriers to care, particularly in low- and middle-income countries, where geographic, financial, and infrastructure constraints further limit access. This article reviews the effects of CP ± L on speech, the essential contributions of SLPs, and the systemic challenges restricting service delivery, and proposes practical strategies for optimizing outcomes in resource-constrained settings. Service gaps are driven by workforce shortages, excessive caseloads, training deficits in cleft-specific care, and poor integration of speech services into healthcare systems. Promising strategies to mitigate these barriers include expanding cleft-specific training within university curricula and continuing education, implementing mentorship and "train-the-trainer" programs, and adopting task-shifting models that equip paraprofessionals, teachers, and caregivers to support therapy under SLP supervision. Telehealth provides opportunities for remote assessment, therapy, and professional supervision, whereas group therapy and structured parent-led home practice extend the impact of limited sessions. Standardized protocols for assessment and outcome reporting are essential for quality improvement and international data comparability. Policy initiatives that prioritize funding, workforce development, and integration of speech services into national health frameworks are critical for ensuring equitable, sustainable access to care. By adopting innovative, evidence-based approaches, including telehealth, mentorship, and parental involvement, healthcare providers can expand cleft speech services worldwide and improve long-term communication outcomes for children affected by CP ± L.

Background/Objectives: Clinical childbirth in high-income countries is increasingly shaped by standardised routines that do not always accommodate individual preferences. In Germany, approximately one in eight pregnant persons experiences clinically significant childbirth-related post-traumatic stress disorder symptoms, with pregnant persons facing language or health-literacy barriers being at particular risk of inadequate preference integration. Methods: This paper presents the conceptual foundation and proposed study design for FAIR-Birth, an interdisciplinary initiative to develop and feasibility-test a mobile application supporting Advance Birth Planning (ABP) embedded within midwifery-led antenatal care. The intervention combines four elements: transfer of the Advance Care Planning concept to antenatal care, a domain-restricted Large Language Model (LLM) supporting multilingual preference articulation, integration of the resulting ABP document into midwifery-led continuity of care, and iterative adaptation. Following the updated MRC framework, this study will employ a sequential mixed-methods design encompassing systematic review, participatory instrument development, Delphi consensus on the knowledge base, iterative technical development with usability testing, and a feasibility study across two perinatal centres in Bavaria. Results/Conclusions: FAIR-Birth is expected to generate a content-validated ABP instrument, a domain-restricted multilingual LLM dialogue system, and an evaluated application prototype. The work corresponds to the development and feasibility phases of the MRC framework; effectiveness questions are reserved for a planned subsequent randomised controlled trial.

Most individuals with amyotrophic lateral sclerosis (ALS) develop bulbar impairment as their disease progresses. The ALS Functional Rating Scale-Revised (ALSFRS-R) bulbar subscore and neurological examination of upper (UMN) and lower motor neurons (LMN) are routinely used to assess this dysfunction but have inherent limitations. Speech‑derived measures have shown promise for capturing bulbar decline with greater sensitivity, but their neurobiological correlates remain unclear. This study examined the associations between quantitative speech measures and cortical thinning in ALS. Data from the Canadian ALS Neuroimaging Consortium were analyzed. Speech measures were extracted from audio recordings of the standardized "Bamboo Passage". Cortical thickness was calculated from T1‑weighted MRI scans. General linear models first compared cortical thickness between patients with ALS and healthy controls. Associations between the speech measures and cortical thickness were then assessed within the ALS group. Patients with ALS showed cortical thinning across bilateral frontotemporal regions, with the largest clusters in the bilateral motor cortices. Reduced speaking and articulation rates were associated with thinning in both oral motor cortices. In contrast, the ALSFRS-R bulbar subscore and UMN and LMN bulbar burden showed no significant associations. Measures of pausing behavior were negatively associated with frontal cortical regions. Thinning of the oral motor cortex in ALS was linked to reduced oral motor function, supporting speaking and articulation rate as sensitive markers of bulbar motor neuron degeneration. These measures demonstrated neuroanatomical associations that the ALSFRS-R bulbar subscore and neurological examination findings did not, highlighting their potential value for monitoring bulbar dysfunction in ALS.

To report a case of carbamazepine-induced neurotoxicity presenting as paroxysmal dysarthria with ataxia, and to highlight clinical risk factors and diagnostic challenges. This case mimicked a transient ischemic attack (TIA), representing a significant diagnostic pitfall. We present the case of a 71-year-old woman who developed acute paroxysmal dysarthria and ataxia after initiating carbamazepine for otoneuralgia. Differential diagnoses considered included TIA, seizure, drug-induced neurotoxicity, and vestibular disorders. Diagnosis was established through medication review, temporal correlation, and a positive rechallenge test. The Naranjo Adverse Drug Reaction Probability Scale was applied. Symptoms resolved completely upon drug withdrawal and recurred immediately after re-exposure (the patient self-administered a single 100 mg dose on day 4, with immediate symptom recurrence, confirming causality). Serum drug levels were not measured due to limitations of our hospital's laboratory facilities; the Naranjo score was 5 (probable ADR). This case illustrates that carbamazepine may induce specific neurotoxicity even at standard doses in susceptible elderly patients. Paroxysmal dysarthria is a rare but underrecognized adverse reaction. Key clinical take-home points include vigilant clinical assessment, caution with potential drug-drug interactions, therapeutic drug monitoring, and pharmacogenetic profiling when indicated- all of which may aid in prevention and risk reduction.

This systematic review synthesized cross-linguistic evidence on speech error patterns in children with speech sound disorders (SSDs), focusing on percent consonants correct (PCC), SODA (substitution, omission, distortion, and addition) error profiles, and phonological processes, as well as factors contributing to variations in error patterns.

Due to articulation issues and phoneme variability, speech disorders such as dysarthria pose significant challenges in clinical rehabilitation. Traditional automatic speech recognition (ASR) systems, which are typically trained on normative datasets, often fail to accurately decode dysarthric speech. Recent breakthroughs in artificial intelligence and deep learning have allowed the integration of multimodal architectures, such as merging auditory, articulatory, and visual information to record complex speech patterns, making it increasingly possible. In this review, we have explored the convergence of transformers and temporal convolutional networks (TCNs) within multimodal frameworks to address phoneme labeling imprecision in dysarthric speech. Here, we discuss how transformer-based contextual modeling and TCN-driven temporal precision can enhance phoneme boundary detection, classification, and rehabilitation feedback. The review also discusses the potential of such hybrid systems in individualized speech therapy, interpretability issues, and clinical applications. Multimodal architectures are a translational approach to enhancing therapeutic monitoring, communication aids, and speech intelligibility assessment for people with motor speech disorders by bridging clinical medicine and medical informatics.

Automated measurement of speaking and articulation rates holds promise as a scalable alternative to manual analysis in clinical populations. This study evaluated a Praat-based script that estimates global speech timing by detecting syllable nuclei via amplitude dips. Speaking rate (syllables/total duration) and articulation rate (syllables/speaking time) were measured manually and with an automated script across speakers with multiple sclerosis (MS), Parkinson's disease (PD), and healthy controls. Sixty participants (20 per group) completed sentence, paragraph, and monologue tasks (N = 180 recordings). Default script parameters were compared to an optimized version with manually tuned dip thresholds. Analyses included error metrics, linear mixed-effects models, and generalizability analysis. Automated speaking rate measures showed strong correlations with manual measures across all groups and tasks (r = 0.623-0.998). However, default automated estimates underestimated both speaking and articulation rates, especially in clinical speakers and for the monologue task. Articulation rate was more sensitive to the measurement method, which accounted for nearly half of the total variance. Optimization of the Praat script parameters reduced proportional error by ∼60%, with varying effects across groups. Findings suggest that optimized automated methods can improve measurement accuracy, but population- and task-specific challenges persist, especially for articulation rate in MS and PD speakers.