Search Results (245)

Theologians have a moral responsibility to attend to the grave disorder in which the language of morality currently suffers. I argue that the healing of this disorder involves a morally prescribable disloyalty to the semblance of the virtue of charity. In this paper, I will review the moral blind spots and ethical inconsistencies in how the semblance of the virtue of charity is confused with the actual virtue of charity and is thus actualized inappropriately in today’s society. I will then investigate the virtue of solidarity as a prescription to help repair the potentiality of what the virtue of charity ought to be and look like. In looking to solidarity, I will turn to Ada María Isasi-Díaz’ epistemological concept of lo cotidiano as a means of practicing accountability in virtue theory and virtue practice. First, I will explore mujerista theology as an approach and why it is important to ethically attend to the voices on the margins; then, I will investigate the concept of lo cotidiano as a methodology that centers a commitment of responsibility to the other; lastly, I will turn to the virtue of solidarity and argue how attending to solidarity enhances our call to charity in an authentic and accountable way (A version of this paper was presented at the 2025 Convention of the Catholic Theological Society of America (CTSA) in Portland, Oregon). Full article

Background/Objectives: The aim of this study was to assess the short-term and long-term effectiveness of group voice therapy in changing vocal behaviour and improving voice quality (VQ) among teachers with hyperfunctional voice disorders (HFVD), using both subjective and objective measures. Methods: Thirty-one teachers participated in a structured group voice therapy programme. Participants underwent videoendostroboscopic evaluation of laryngeal morphology and function, perceptual assessment of voice, acoustic analysis of voice samples, and aerodynamic measurements of phonation. Patients’ self-assessment of VQ and its impact on quality of life were measured using a Visual Analogue Scale (VAS) and the Voice Handicap Index-30 (VHI-30). Evaluations were conducted at four time points: pre-therapy (T0), immediately post-therapy (T1), and at 3-month (T3) and 12-month (T12) follow-up visits. Results: Significant improvement was observed between T0 and T1 in perceptual voice evaluations: grade, roughness, asthenia, strain, loudness, fast speaking rate, as well as in neck muscle tension, shimmer, patients’ most harmful vocal behaviours, VHI-30 scores, patients VQ evaluation, and its impact on quality of life (all p < 0.05). Almost all parameters of subjective and objective voice assessment improved over the 12-month observation period, with the greatest improvement between T0 and T12 (all p < 0.05), indicating lasting reduced laryngeal tension and improved phonatory efficiency. Conclusions: Group voice therapy has been shown to be an effective treatment for teachers with HFVD, leading to significant and long-lasting improvements in perceptual, acoustic, and self-assessment outcomes. Therapy also promoted healthier vocal and lifestyle behaviours, supporting its role as a successful and cost-effective rehabilitation and prevention method for occupational voice disorders. Full article

Background: Lee Silverman Voice Treatment (LSVT) BIG is a well-established exercise program in Parkinson’s Disease (PD), but its effectiveness in other neurological disorders is not well studied. This pilot study examined whether LSVT-BIG similarly improves balance and gait in MS patients compared to PD. Methods: A pilot clinical trial was conducted with two participant groups: MS and PD. Assessments were performed before, during, and after the 4-week LSVT BIG intervention, which followed the established PD protocol of one-hour sessions, four consecutive days per week. Balance and gait were evaluated using the mini-Balance Evaluation Systems Test (mini-BESTest), Timed Up and Go (TUG), and Functional Gait Assessment (FGA). Single-leg stance time on firm, foam, and inclined surfaces was also measured. Data analysis was carried out using mixed ANOVA in SPSS v24. Results: Twelve participants completed the study (6 PD, 6 MS). Both groups significantly improved in mini-BESTest, FGA scores, and timed tasks (p < 0.001). Comparable between-group results revealed, with no significant differences between MS and PD groups (p > 0.5). Conclusions: Similar improvements across groups suggest that LSVT BIG may also benefit patients with MS. Larger randomized trials are needed to confirm its suitability for this population. Full article

In this study, we propose a novel automated model for speech quality estimation that objectively evaluates perceptual dysphonia severity and breathiness in audio samples, demonstrating strong correlation with expert ratings. The proposed model integrates Whisper encoder embeddings with Mel spectrograms augmented by second-order delta features combined with a sequential-attention fusion network feature mapping path. This hybrid approach enhances the model’s sensitivity to phonetic, high-level feature representation, and spectral variations, enabling more accurate predictions of perceptual speech quality. A sequential-attention fusion network feature mapping module captures long-range dependencies through the multi-head attention network, while LSTM layers refine the learned representations by modeling temporal dynamics. Comparative analysis against state-of-the-art methods for dysphonia assessment demonstrates our model’s better correlation with clinician’s judgments across test samples. Our findings underscore the effectiveness of ASR-derived embeddings alongside the deep feature mapping structure in disordered speech quality assessment, offering a promising pathway for advancing automated evaluation systems. Full article

(1) Background: Most eye-movement studies in dyslexia focus on silent reading in controlled laboratory settings. Yet, oral reading of standardized texts remains central for identifying this disorder. By combining eye-tracking with oral reading, we captured both fixation dynamics and eye–voice span (EVS) measures, offering a richer view of the processes underlying dyslexia. (2) Methods: We tested 10 adults with dyslexia and 14 controls as they read aloud an unpredictable diagnostic text in French. Analyses examined psycholinguistic effects of word length and lexical frequency on fixation probabilities, counts, and durations, alongside EVS measures. (3) Results: Compared to controls, adults with dyslexia read more slowly, made more errors, and showed atypical fixation patterns: persistent word length effects, reduced frequency effects, and diminished, unstable EVS. (4) Conclusions: Together, eye-movement and EVS findings converge on a key mechanism: adults with dyslexia continue to rely heavily on sublexical decoding. This reliance creates a processing bottleneck in oral reading, where difficulties in rapid word identification cascade into sounding-out behavior and disrupted eye–voice coordination. Full article

In individuals with Parkinson’s disease (PD), bradykinesia severity is related to physical activity (PA) inside homes. We aimed to investigate the effectiveness of the Lee Silverman Voice Treatment (LSVT)^® BIG intervention in increasing at-home PA in individuals with PD. To evaluate the effect of the intervention, we compared pre- and post-intervention scores on the Movement Disorder Society-sponsored revision of the Unified Parkinson’s Disease Rating Scale (MDS-UPDRS) Parts 3 and 2, as well as the time spent at home in three categories of PA intensity. For statistical testing, paired t-tests were used when the data met the assumptions of normality, and the Wilcoxon signed-rank test was applied otherwise. Differences were considered statistically significant at p < 0.05. This preliminary retrospective observational study included 10 eligible individuals with PD (4 males). The participants’ mean age was 71.0 ± 10.8 years, with median Hoehn and Yahr stage 3 [interquartile range: 1 to 4]. The MDS-UPDRS Part 3 score, bradykinesia score calculated from a part of that score, and the MDS-UPDRS Part 2 score significantly improved after the intervention (Wilcoxon signed-rank test, p < 0.05). The time spent in sedentary behavior (SB) significantly decreased from 516.4 ± 72.6 to 484.0 ± 70.0 min, whereas that spent in light PA (LPA) significantly increased from 137.8 ± 46.2 to 169.5 ± 32.1 min (paired t-test, p < 0.05). The time spent on moderate-to-vigorous PA (MVPA) did not change significantly (paired t-test, p = 0.533). The results suggested that LSVT^® BIG is an effective intervention for increasing at-home PA in individuals with PD. In addition, regarding the specific details of the increase, the time spent on MVPA may not change, and the increase may be mainly attributed to increased LPA and reduced sedentary time. Full article

Rates of self-harm in Australian young people have increased significantly in recent years, especially in young women. Self-harm has been associated with several risk factors, including a history of abuse, bullying, mood and personality disorders, social isolation and suicidal ideation. However, little is known about why rates have increased in the past decade, and the voices of young Australian women have been conspicuously absent from the research. This study explored perceived subjective reasons for the increase in self-harm rates by interviewing 24 young Australian women with lived experience of self-harming behaviours. A reflexive thematic analysis identified three interwoven themes: ‘The world is hard, and it’s getting harder’, ‘New media exacerbates old challenges’, and ‘The online world brings unique challenges’. Participants also highlighted the complexity of social media as both a negative influence and a supportive factor. These themes extend previous research by highlighting the nuanced and multi-faceted psychosocial factors that influence self-harming behaviours and may help inform effective, evidence-based strategies that help minimise harm. Full article

This study examines the impact of vocal fold (VF) lesions located on the superior surface on glottal airflow dynamics and tissue oscillatory behaviors using biomechanical simulations of a two-layered realistic VF model. It is hypothesized that morphological changes in the VFs due to the presence of a lesion cause changes in tissue elasticity and rheological properties, contributing to dysphonia. Previous research has lacked the integration of lesions in computational simulations of anatomically accurate larynx-VF models to explore their effects on phonation and contribution to voice disorders. Addressing the current gap in literature, this paper considers a computational model of a two-layered VF structure incorporating a lesion that represents a hemorrhagic polyp. A three-dimensional, subject-specific, multilayered geometry of VFs is constructed based on STL files derived from a human larynx CT scan, and a fluid–structure interaction (FSI) methodology is employed to simulate the coupling of glottal airflow and VF tissue dynamics. To evaluate the effects of the lesion’s presence, two FSI models, one with a lesion embedded in the cover layer and one without, are simulated and compared. Analysis of airflow dynamics and tissue vibrational patterns between these two models is used to determine the impact of the lesion on the biomechanical characteristics of phonation. The polyp is found to slightly increase airflow resistance through the glottis and disrupt vibratory symmetry by decreasing the vibration frequency of the affected fold, leading to weaker and less rhythmic oscillations. The results also indicate that the lesion increases tissue stress in the affected fold, which agrees with clinical observations. While quantitative ranges depend on lesion size and tissue properties, these consistent and physically meaningful trends highlight the biomechanical mechanisms by which lesions influence phonation. Full article

Background: Autism spectrum disorder (ASD) and related neurodevelopmental conditions are a significant public health concern, with diagnostic delays hindering timely intervention. Traditional assessments often lead to waiting times exceeding a year. Advances in artificial intelligence (AI) and biomarker-based screening offer objective, efficient alternatives for early identification. Objective: This review synthesizes the latest evidence for AI-enabled technologies aimed at improving early ASD identification. Modalities covered include eye-tracking, acoustic analysis, video- and sensor-based behavioral screening, neuroimaging, molecular/genetic assays, electronic health record prediction, and home-based digital applications or apps. This manuscript critically evaluates their diagnostic accuracy, clinical feasibility, scalability, and implementation hurdles, while highlighting regulatory and ethical considerations. Findings: Across modalities, machine learning approaches demonstrate strong accuracy and specificity in ASD detection. Eye-tracking and voice-acoustic classifiers reliably differentiate for autistic children, while home-video analysis and Electronic Health Record (EHR)-based algorithms show promise for scalable screening. Multimodal integration significantly enhances predictive power. Several tools have received Food and Drug Administration clearance, signaling momentum for wider clinical deployment. Issues persist regarding equity, data privacy, algorithmic bias, and real-world performance. Conclusions: AI-enabled screeners and diagnostic aids have the potential to transform ASD detection and access to early intervention. Integrating these technologies into clinical workflows must safeguard equity, privacy, and clinician oversight. Ongoing longitudinal research and robust regulatory frameworks are essential to ensure these advances benefit diverse populations and deliver meaningful outcomes for children and families. Full article

Introduction: ‘Associative prosopagnosia’ and ‘associative phonagnosia’ are high-level post-perceptual face and voice recognition defects due to right anterior temporal lesions, but the relations between these two disorders are uncertain. It is, indeed, not clear if face and voice recognition disorders observed in these patients must be considered as independent modality-specific recognition defects or as fragments of a more general semantic disorder concerning the multimodal representation of known persons. Aims of this study: In this review, the relations between associative forms of face and voice recognition disorders were investigated in all patients with right anterior temporal lesions reported in the literature. A prevalence of ‘pure’ (modality-specific) forms could indicate that these are independent, modality-specific recognition defects, whereas a high frequency of voice- and face-associated disorders could suggest that they are components of a multimodal semantic disruption. Results: Results show that ‘associative prosopagnosia’ and ‘associative phonagnosia’ are observed sometimes as ‘pure’ forms, other times as associations between verbal and non-verbal defects of person recognition, and still other times as associations restricted to the non-verbal (face and voice) modalities of person recognition. Furthermore, in a patient with a multimodal face and voice recognition disorder, the lesion involved the right temporal pole, considered as the locus of convergence of face and voice recognition modalities. Discussion: These data suggest that specific lesions of the right anterior temporal lobes can disrupt the highest modality-specific levels of face and voice representations, whereas other equally selective lesions can disrupt the locus of convergence of face and voice recognition modalities. Full article

This exploratory study investigated whether voice-derived acoustic features reflect depressive symptom severity and whether they carry preliminary predictive signal for distinguishing individuals with Major Depressive Disorder (MDD) from healthy controls (HC). Using the publicly available MODMA dataset (23 MDD; 29 HC), 6553 acoustic features were extracted with openSMILE. Spearman correlation and group-difference analyses identified several MFCC-derived spectral features as moderately and systematically associated with PHQ-9 scores, indicating their potential relevance as severity-linked acoustic markers. To complement these findings, a supplementary severity-based classification using a PHQ-9 ≥ 10 threshold showed that a logistic regression model trained on the top five correlated MFCC features achieved a cross-validated AUC of 0.78 (SD = 0.15), supporting their association with clinically defined symptom burden. Four machine learning pipelines were further evaluated for an exploratory MDD–HC classification task. Among them, the PCA + XGBoost model demonstrated the most stable generalization (test AUC = 0.60), although predictive performance remained limited within the constraints of the small and high-dimensional dataset. SHAP analysis highlighted MFCC-derived features as key contributors to model decisions, providing transparent interpretability. Overall, the study presents preliminary evidence linking acoustic characteristics to depressive symptoms and outlines a reproducible analytical workflow, while underscoring the need for substantially larger and more diverse datasets to establish clinically meaningful predictive validity. Full article

Parkinson’s disease (PD) is a progressive neurodegenerative disorder characterized by motor and non-motor symptoms, among which vocal impairment is one of the earliest and most prevalent. In recent years, voice analysis supported by machine learning (ML) and deep learning (DL) has emerged as a promising non-invasive method for early PD detection. We conducted a systematic review searching PubMed, Scopus, IEEE Xplore, and Web of Science databases for studies published between 2020 and September 2025. A total of 69 studies met the inclusion criteria and were analyzed in terms of dataset characteristics, speech tasks, feature extraction techniques, model architectures, validation strategies, and performance outcomes. Classical ML models such as Support Vector Machines (SVMs) and Random Forests (RFs) achieved high accuracy on small, homogeneous datasets, while DL architectures, particularly Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Transformer-based foundation models, demonstrated greater robustness and scalability across languages and recording conditions. Despite these advances, persistent challenges such as dataset heterogeneity, class imbalance, and inconsistent validation practices continue to hinder reproducibility and clinical translation. Overall, the field is transitioning from handcrafted feature-based pipelines toward self-supervised, representation-learning frameworks that promise improved generalizability. Future progress will depend on the development of large, multilingual, and openly accessible datasets, standardized evaluation protocols, and interpretable AI frameworks to ensure clinically reliable and equitable voice-based PD diagnostics. Full article

Background: Parkinson’s disease (PD) is a degenerative neurological disorder that greatly affects motor and speech functions; therefore, early diagnosis is vital for improving patients’ quality of life. This work introduces a unified and explainable AI framework for PD detection that integrates ensemble and deep learning models with transparent interpretability techniques. Methods: Acoustic features were extracted from the Parkinson’s Voice Disorder Dataset, and a broad suite of machine learning and deep learning models was evaluated, including traditional classifiers (Logistic Regression, Decision Tree, KNN, Linear Regression, SVM), ensemble methods (Random Forest, Gradient Boosting, XGBoost, LightGBM), and neural architectures (CNN, LSTM, GAN). Results: The ensemble methods—specifically LightGBM (LGBM) and Random Forest (RF)—achieved the best performance, reaching state-of-the-art accuracy (98.01%) and ROC-AUC (0.9914). Deep learning models like CNN and GAN produced competitive results, validating their ability to capture nonlinear and generative voice patterns. XAI analysis revealed that nonlinear acoustic biomarkers such as spread2, PPE, and RPDE are the most influential predictors, consistent with clinical evidence of dysphonia in PD. Conclusions: The proposed framework achieves a strong balance between predictive accuracy and interpretability, representing a clinically relevant, scalable, and non-invasive solution for early Parkinson’s detection. Full article

Voice acoustics have been extensively investigated as potential non-invasive markers for Autism Spectrum Disorder (ASD). Although many studies report high accuracies, they typically rely on highly controlled clinical protocols that reduce linguistic variability. Their data is also recorded using specialized microphone arrays that ensure high-quality recordings. Such dependencies limit their applicability in real-world or in-home screening contexts. In this work, we explore an alternative approach designed to reflect the requirements of mobile-based applications that could assist parents in monitoring their children. We use an open-access dataset of naturalistic storytelling, extracting only the speech segments in which the child is speaking. We applied previously published ASD voice-analysis pipelines to this dataset, which yielded suboptimal performance under these less controlled conditions. We then introduce a deep learning-based method that learns discriminative representations directly from raw audio, eliminating the need for manual feature extraction while being more robust to environmental noise. This approach achieves an accuracy of up to 77% in classifying children with ASD, children with Attention Deficit Hyperactivity Disorder (ADHD), and neurotypical children. Frequency-band occlusion sensitivity analysis on the deep model revealed that ASD speech relied more heavily on the 2000–4000 Hz range, TD speech on both low (100–300 Hz) and high (4000–8000 Hz) bands, and ADHD speech on mid-frequency regions. These spectral patterns may help bring us closer to developing practical, accessible pre-screening tools for parents. Full article

This scoping review systematically maps the rapidly evolving application of Artificial Intelligence (AI) in Autism Spectrum Disorder (ASD) diagnostics, specifically focusing on computational behavioral phenotyping. Recognizing that observable traits like speech and movement are critical for early, timely intervention, the study synthesizes AI’s use across eight key behavioral modalities. These include voice biomarkers, conversational dynamics, linguistic analysis, movement analysis, activity recognition, facial gestures, visual attention, and multimodal approaches. The review analyzed 158 studies published between 2015 and 2025, revealing that modern Machine Learning and Deep Learning techniques demonstrate highly promising diagnostic performance in controlled environments, with reported accuracies of up to 99%. Despite this significant capability, the review identifies critical challenges that impede clinical implementation and generalizability. These persistent limitations include pervasive issues with dataset heterogeneity, gender bias in samples, and small overall sample sizes. By detailing the current landscape of observable data types, computational methodologies, and available datasets, this work establishes a comprehensive overview of AI’s current strengths and fundamental weaknesses in ASD diagnosis. The article concludes by providing actionable recommendations aimed at guiding future research toward developing diagnostic solutions that are more inclusive, generalizable, and ultimately applicable in clinical settings. Full article