Search Results (254)

Background/Objectives: Cognitive impairment affects multiple brain functions, and its early detection is essential to prevent progression to dementia; artificial intelligence has shown considerable potential in this field. This scoping review aims to map the impact of artificial intelligence–based tools for the early detection of cognitive impairment by identifying the main technologies used, examining their effectiveness, and exploring their ethical implications. Methods: A scoping review was conducted between April and May 2025 following the PRISMA-ScR methodological framework; the review protocol was previously registered on the Open Science Framework. PubMed, Scopus, and Cochrane databases were searched using natural language and controlled vocabulary terms via Medical Subject Headings. The search was limited to articles published between 2020 and 2025, in English or Spanish, with free full-text access. Methodological quality was assessed using CASPe, JBI, and MMAT. Results: A total of 14 studies were included after the selection and critical appraisal process. The findings show that artificial intelligence–based tools such as deep-learning models applied to neuroimaging, speech and gait analysis, electronic health record analysis, and mobile health applications demonstrate promising accuracy in detecting early cognitive changes. These technologies enable the identification of subtle patterns that may be difficult to detect using conventional clinical assessments. Conclusions: AI-based tools can provide substantial support for clinical decision-making by effectively identifying subtle changes that are imperceptible to human intelligence. However, their use also raises ethical issues related to patient privacy and data security. Full article

Developmental Language Disorder (DLD) is a common neurodevelopmental condition that affects language acquisition in children. However, standardized diagnostic tools for Tunisian Arabic, a widely spoken yet underrepresented dialect, is still lacking. This study presents a multimodal biomedical informatics framework that integrates clinical assessments, speech recordings, and artificial intelligence (AI) for early DLD detection. Three linguistic tasks (the CLT Task, the Arabic Verb Evaluation Task, and the Nonword Repetition Task) were adapted for Tunisian Arabic, and spontaneous speech samples were collected from children with typical development and those with DLD. Statistical analyses revealed significant deficits in verb production, past-tense morphology, and phonological memory in the DLD group. For automated screening, we developed two systems: a Random Forest classifier based on structured clinical and linguistic features and a multimodal deep learning model using Wav2Vec2 acoustic embeddings. The best model achieved an F1 score of 0.85, demonstrating the feasibility of AI-assisted DLD screening. This work introduces the first standardized dataset and computational baseline for DLD in Tunisian Arabic, providing clinically relevant tools for early identification and supporting research on underrepresented Arabic dialects. This work also highlights future implications, including potential applications in early screening, the integration of acoustic markers, and the development of culturally adapted assessment tools for underrepresented languages. Full article

Background: This research explores the complex relationship between Attention Deficit Hyperactivity Disorder (ADHD) and language skills, focusing on the impact of the disorder on children’s language development. It is designed as a systematic literature review to synthesize and evaluate existing evidence on this topic. Based on the existing literature, ADHD affects multiple dimensions of language, including phonological awareness, pragmatic comprehension, morphosyntactic structure, narrative skills, and written expression. The difficulties that children with ADHD exhibit at the language level are directly related to their deficits in working memory, attention, and organization, which make it challenging for them to acquire and use language at both educational and social levels. Methods: This study followed the PRISMA methodology, with a systematic selection process across four stages (identification, screening, eligibility, and inclusion). During the identification phase, 475 records were identified (450 from database searches and 25 through reference screening). After screening and applying inclusion criteria, 15 studies met all eligibility requirements and were included in the final synthesis. Results: The present research highlighted the important role that occupational therapists and psychologists can play in the language development of children with ADHD. Strategic interventions to alleviate the language difficulties of children with ADHD are designed to enhance phonological awareness, executive function, speech and language, the use of technological tools, and social skills training. Conclusions: The importance of early diagnosis and implementation of holistic, individualized interventions targeting the language, executive, and social difficulties manifested by children with ADHD is considered influential in addressing the barriers to improving language skills as effectively as possible. Full article

This study aims to develop effective screening tools for cognitive impairment by integrating optimised speech classification features with various machine learning models. A total of 65 patients diagnosed with early-stage Mild Cognitive Impairment (MCI) and 55 healthy controls (HCs) were included. Audio data were collected through a picture description task and processed using the Python-based Librosa library for speech feature extraction. Three machine learning models were constructed: the Random Forest (RF) and Support Vector Machine (SVM) models utilised speech classification features optimised via the Sequential Forward Selection (SFS) algorithm, while the Extreme Gradient Boosting (XGBoost) model was trained on preprocessed speech data. After parameter tuning, the Librosa library successfully extracted 41 speech classification features from all participants. The application of the SFS optimisation strategy and the use of preprocessed data significantly improved identification accuracy. The SVM model achieved an accuracy of 0.825 (AUC: 0.91), the RF model reached 0.88 (AUC: 0.86), and the XGBoost model attained 0.92 (AUC: 0.91). These results suggest that speech-based machine learning models markedly improve the accuracy of distinguishing MCI patients from healthy older adults, providing reliable support for early cognitive deficit identification. Full article

The graph Hilbert transform (GHT) is a key tool in constructing analytic signals and extracting envelope and phase information in graph signal processing. However, its utility is limited by confinement to the graph Fourier domain, a fixed phase shift, information loss for real-valued spectral components, and the absence of tunable parameters. The graph fractional Fourier transform introduces domain flexibility through a fractional order parameter $\alpha$ but does not resolve the issues of phase rigidity and information loss. Inspired by the dual-parameter fractional Hilbert transform (FRHT) in classical signal processing, we propose the graph FRHT (GFRHT). The GFRHT incorporates a dual-parameter framework: the fractional order $\alpha$ enables analysis across arbitrary fractional domains, interpolating between vertex and spectral spaces, while the angle parameter $\beta$ provides adjustable phase shifts and a non-zero real-valued response ($cos\beta$) for real eigenvalues, thereby eliminating information loss. We formally define the GFRHT, establish its core properties, and design a method for graph analytic signal construction, enabling precise envelope extraction and demodulation. Experiments on anomaly identification, speech classification and edge detection demonstrate that GFRHT outperforms GHT, offering greater flexibility and superior performance in graph signal processing. Full article

Diabetes is known to affect metabolic, vascular, and nervous systems, although its influence on auditory function in children remains poorly defined. Understanding this association is essential due to its implications for cognitive, language, and social development. Numerous studies have found that children with Type 1 Diabetes Mellitus (T1DM) exhibit higher hearing thresholds at high frequencies (4000–8000 Hz) and lower speech understanding scores compared to healthy controls. Poor glycemic control and longer disease duration are consistently associated with worse auditory outcomes. The proposed mechanisms include microangiopathy and diabetic neuropathy affecting the auditory pathway. Many affected children do not report noticeable auditory symptoms, indicating a risk of underdiagnosis. Early identification is crucial, as hearing difficulties in children may be related to underlying diabetic conditions and are likely associated with poor glycemic control. Regular audiometric screening should be incorporated into the routine care of pediatric diabetes patients to identify hearing deficits before they affect communication and cognitive development. Full article

We survey recent advances in second-language (L2) Mandarin lexical tones research and show how an interpretable computational approach can deliver parameter-aligned feedback across perception–production (P ↔ P). We synthesize four strands: (A) conventional evaluations and tasks (identification, same–different, imitation/read-aloud) that reveal robust tone-pair asymmetries and early P ↔ P decoupling; (B) physiological and behavioral instrumentation (e.g., EEG, eye-tracking) that clarifies cue weighting and time course; (C) audio-only speech analysis, from classic F0 tracking and MFCC–prosody fusion to CNN/RNN/CTC and self-supervised pipelines; and (D) interpretable learning, including attention and relational models (e.g., graph neural networks, GNNs) opened with explainable AI (XAI). Across strands, evidence converges on tones as time-evolving F0 trajectories, so movement, turning-point timing, and local F0 range are more diagnostic than height alone, and the contrast between Tone 2 (rising) and Tone 3 (dipping/low) remains the persistent difficulty; learners with tonal vs. non-tonal language backgrounds weight these cues differently. Guided by this synthesis, we outline a tool-oriented framework that pairs perception and production on the same items, jointly predicts tone labels and parameter targets, and uses XAI to generate local attributions and counterfactual edits, making feedback classroom-ready. Full article

This study examined how variability in phonetic training input (high vs. low) influences the perception and acquisition of Spanish stop consonants by English-speaking beginners. A total of 128 participants completed 20 online identification sessions targeting /p, t, k, b, d, g/. In the high-variability condition (HVPT), learners heard tokens from six speakers, and in the low-variability condition (LVPT), all input came from a single speaker. Training followed an interleaved-talker design with immediate feedback, and perceptual learning was evaluated using a Bayesian hierarchical logistic regression analysis. Results showed improvement across sessions for both groups, with identification accuracy reaching ceiling by the end of the training sessions. Differences between HVPT and LVPT were small: LVPT showed steeper categorization trajectories in some cases due to slightly lower baselines, but neither condition yielded a measurable advantage. The pattern observed suggests that for boundary-shift contrasts such as Spanish stops, perceptual improvements are driven primarily by input quantity rather than variability. This interpretation aligns with input-based models of L2 speech learning (SLM-r, L2LP) and underscores the role of repeated exposure in restructuring phonological categories. Full article

Fundamental frequency estimation, also known as F0 estimation, is a crucial task in speech processing and analysis, with significant applications in areas such as speech recognition, speaker identification, and emotion detection. Traditional algorithms, while effective, often encounter challenges in real-time environments due to computational limitations. Recent advances in deep learning, especially in the use of recurrent neural networks (RNNs), have opened new opportunities for enhancing F0 estimation accuracy and efficiency. This paper introduces a novel RNN-based F0 estimation method with an attention mechanism and evaluates its performance against selected state-of-the-art F0 estimation approaches, including standard baseline methods, as well as neural-network-based regression and classification models. By integrating attention mechanisms, the model eliminates the necessity for post-processing steps and enables a more efficient seq2scal estimation process. While the self-attention mechanism used in Transformers captures all pairwise temporal dependencies at a quadratic computational cost, the proposed method’s implementation of the attention mechanism enables it to selectively focus on the most relevant acoustic cues for F0 prediction, enhancing robustness without increasing the model’s complexity. Experimental results using the LibriSpeech and Common Voice datasets demonstrate superior computational efficiency of the proposed method compared to current state-of-the-art RNN-based seq2seq models, while maintaining comparable estimation accuracy. Furthermore, the proposed “RNN-based F0 estimation method with an attention mechanism” achieves the lowest computational complexity among all compared models, while maintaining high accuracy, making it suitable for low-latency, resource-limited deployments and competitive even with standard baseline methods, such as pYIN or CREPE. Finally, the performance of the developed RNN-based F0 estimation method with attention mechanism in terms of RMSE and FLOPs demonstrates the potential of attention mechanisms and sequence modelling in achieving high accuracy alongside lightweight F0 estimation suitable for modern speech processing applications, which aligns with the growing trend towards deploying intelligent systems on resource-constrained devices. Full article

Speaker diarization is a key component of automatic speech recognition (ASR) systems, particularly in interview scenarios where speech segments must be assigned to individual speakers. This study presents a diarization algorithm based on sound intensity analysis using an Acoustic Vector Sensor (AVS). The algorithm determines the azimuth of each speaker, defines directional beams, and detects speaker activity by analyzing intensity distributions within each beam, enabling identification of both single and overlapping speech segments. A dedicated dataset of interview recordings involving five speakers was created for evaluation. Performance was assessed using the Diarization Error Rate (DER) metric and compared with the State-of-the-Art Pyannote.audio system. The proposed AVS-based method achieved a lower DER value (0.112) than Pyannote (0.213) without overlapping speech, and a DER equal to 0.187 with overlapping speech included, demonstrating improved diarization accuracy and better handling of overlapping speech. The algorithm does not require training, operates independently of speaker-specific features, and can be adapted to various acoustic conditions. The results confirm that AVS-based diarization provides a robust and interpretable alternative to neural approaches, particularly suitable for structured two-speaker dialogues such as physician–patient or interviewer–interviewee scenarios. Full article

Background/Objectives: Dysphagia represents a significant global health concern with particularly high prevalence in specific clinical conditions, yet educational gaps persist among healthcare professionals and caregivers. This observational, cross-sectional quantitative study aimed to provide a comprehensive overview of the current self-perceived knowledge and learning needs among stakeholders involved in dysphagia management. Methods: An international online survey was conducted in five European countries (Greece, Italy, Lithuania, Spain, and Turkey) with 463 participants: 297 professionals (healthcare and non-health specialists, educators, students) and 166 non-professionals (patients, family members, caregivers, interested individuals). Two structured questionnaires explored self-perceived knowledge, learning needs, relevancy of thematic areas, and preferred learning methods. Chi-square and Fisher’s exact tests were used for statistical comparisons. Results: Professionals reported higher self-perceived knowledge than non-professionals (p < 0.001), yet both groups expressed comparable needs for further education. Priority learning areas varied by respondent profile: “Identification & Treatment” was prioritized by both speech-language pathologists and healthcare specialists, as well as by non-professionals, while dietitian-nutritionists focused on “Diet & Nutrition” and “Food Preparation”. Short-duration courses and visual, hands-on learning tools were preferred across groups. Conclusions: This study highlights a broad demand for dysphagia education among professionals and non-professionals. Tailored, technology-enhanced learning programs could bridge existing knowledge gaps, strengthen multidisciplinary collaboration, and support better daily management of dysphagia. Full article

Second language (L2) learners often struggle to process prosodic boundaries, which are essential for speech comprehension. This study investigated the nature of these difficulties and how first language (L1) cue-weighting strategies transfer to L2 processing among Chinese (Mandarin)–English learners. The rising pitch that cues English phrase boundaries acoustically overlaps with functionally distinct Chinese lexical tones. Through two experiments comparing Chinese–English learners and native English speakers, we assessed sensitivity across lexical constituent, phrase, and sentence boundaries and manipulated acoustic cues (pause, lengthening, pitch) to estimate their perceptual weights during phrase-boundary identification. L2 learners showed reduced discrimination sensitivity only at the phrase level, performing comparably to native speakers at lexical constituent and sentence boundaries. For phrase boundaries, learners over-relied on pitch and under-relied on pre-boundary lengthening compared to native speakers, though both groups weighted pauses strongly. This selective deficit implicates the transfer of L1 cue-weighting strategies more than a global knowledge deficit. Our findings support a dynamic transfer model where L1 sensitivity to lexical tone transfer of L2 phrase perception, elevating the weight of pitch. While learners show partial adaptation, these results refine the Cue-Weighting Transfer Hypothesis by demonstrating that L2 prosodic acquisition involves both integrated L1 transfer and L2-driven reweighting strategies. Full article

Background/Objectives: Avoidant/Restrictive Food Intake Disorder (ARFID) frequently co-occurs with Autism Spectrum Disorder (ASD), yet its detection and assessment remain challenging. This study aimed to analyze terminology and professionals’ views on features and indicators related to ARFID among Spanish professionals working with autistic individuals, identifying potential gaps and training needs. Methods: A cross-sectional study was conducted with 194 professionals (62 speech therapists, 62 psychologists, and 70 occupational therapists) from different regions of Spain, who completed a 13-item questionnaire on their familiarity with terminology, definitions, and features they consider indicative to ARFID. Descriptive analyses and chi-square tests were applied to explore interprofessional differences. Results: Significant differences emerged across disciplines (p < 0.001). Psychologists showed greater familiarity with DSM-5 diagnostic criteria (78%), while speech-language therapists (72%) and occupational therapists (69%) more frequently endorsed sensory, oromotor, and behavioral features as relevant. Across all groups, 61% reported uncertainty about ARFID diagnostic criteria, and only 34% reported familiarity with validated assessment tools. Conclusions: Spanish professionals working with ASD populations demonstrate heterogeneous and generally limited understanding of the features they associate with ARFID, with discipline-specific approaches to assessment. These findings provide initial evidence in Spanish-speaking contexts and underscore the need for structured training and validated Spanish-adapted instruments to support early and accurate ARFID identification. Full article

Gender-based violence is a pervasive social and public health issue that severely impacts women’s mental health, often leading to conditions such as anxiety, depression, post-traumatic stress disorder, and substance abuse. Identifying the combination of these various mental health conditions could then point to someone who is a victim of gender-based violence. While speech-based artificial intelligence tools appear as a promising solution for mental health screening, their performance often deteriorates when encountering speech from previously unseen speakers, a sign that speaker traits may be confounding factors. This study introduces a speaker-agnostic approach to detecting the gender-based violence victim condition—defined as self-identified survivors who exhibit pre-clinical PTSD symptom levels—from speech, aiming to develop robust artificial intelligence models capable of generalizing across speakers. By employing domain-adversarial training, we reduce the influence of speaker identity on model predictions, and we achieve a 26.95% relative reduction in speaker identification accuracy while improving gender-based violence victim condition classification accuracy by 6.37% (relative). These results suggest that our models effectively capture paralinguistic biomarkers linked to the gender-based violence victim condition, rather than speaker-specific traits. Additionally, the model’s predictions show moderate correlation with pre-clinical post-traumatic stress disorder symptoms, supporting the relevance of speech as a non-invasive tool for mental health monitoring. This work lays the foundation for ethical, privacy-preserving artificial intelligence systems to support clinical screening of gender-based violence survivors. Full article

Background: Gerstmann syndrome (GS) is characterised by the tetrad of agraphia, acalculia, finger agnosia, and right-left disorientation, which was first described by Josef Gerstmann in 1924 and is conventionally linked to lesions of the dominant angular gyrus. Contemporary neuroimaging and lesion mapping research indicates that a more dispersed parietal and occipito-temporal network may be involved. Bilateral parietal lobe infarcts are uncommon and usually arise from embolic events or small artery pathology, frequently resulting in multifocal cognitive and perceptual impairments. Method: This case report describes a 52-year-old male presented with acute confusion, perseverative speech, and an inability to follow commands. The neurological examination indicated the presence of the complete Gerstmann tetrad. The Magnetic Resonance Imaging (MRI brain) revealed bilateral parieto-occipital infarcts, with greater severity on the left, indicative of ischaemia in the territory of the posterior cerebral artery (PCA). The medical team provided supportive care and implemented secondary stroke prevention, leading to partial neurocognitive recovery over a period of three weeks. Results: This case highlights a rare presentation of Gerstmann syndrome due to bilateral parieto-occipital infarcts and emphasises that the syndrome can arise from bilateral or widespread parietal injury rather than lesions limited to the angular gyrus. Conclusions: The prompt identification of the Gerstmann constellation helps localise the lesion, enhances diagnostic accuracy, and aids in rehabilitation planning. Full article