Search Results (51)

Detecting unnatural pauses is a critical component of automated quality assessment (AQA) in interpreter training, as pause patterns directly reflect an interpreter’s cognitive load and fluency. Traditional pause detection methods rely on static temporal thresholds (e.g., 1.0 s), which often fail to account for segment-specific speech rate variability and individual speaking styles. This study proposes a context-adaptive pause detection framework that integrates unsupervised anomaly detection using Isolation Forest (iForest) with a sliding window technique. To enhance pedagogical validity, we specifically focused on intra-sentential pauses by delineating sentence boundaries using a specialized segmentation model. The proposed model was evaluated against ground-truth labels annotated by professional interpreting experts. Our results demonstrate that the sliding window–based contextual anomaly detection model significantly outperforms the conventional static baseline, particularly in terms of recall and Cohen’s kappa. Furthermore, by applying a weighted F3-score and the “Recognition-over-Recall” principle, we confirmed that the proposed model substantially reduces the instructor’s total operational burden by shifting the workload from de novo annotation creation to more efficient corrective pruning. These findings suggest that speech-adaptive modeling provides a more reliable and labor-saving framework for automated interpreting assessment and feedback. Specifically, this study makes three main contributions: (1) the proposal of a context-adaptive pause detection framework using anomaly detection, (2) the integration of sliding window–based local contextual modeling for speech-rate–aware analysis, and (3) the introduction of an evaluation strategy based on the Recognition-over-Recall principle to reduce instructor workload in interpreter training. Full article

Arabic sign language (ArASL) is the primary communication medium for Deaf and hard-of-hearing people across Arabic-speaking communities. Most current ArASL recognition systems are based solely on visual features and do not incorporate linguistic or semantic information that could improve generalization and semantic grounding. This paper introduces CLIP-ArASL, a lightweight CLIP-style multimodal approach for static ArASL letter recognition that aligns visual hand gestures with bilingual textual descriptions. The approach integrates an EfficientNet-B0 image encoder with a MiniLM text encoder to learn a shared embedding space using a hybrid objective that combines contrastive and cross-entropy losses. This design supports supervised classification on seen classes and zero-shot prediction on unseen classes using textual class representations. The proposed approach is evaluated on two public datasets, ArASL2018 and ArASL21L. Under supervised evaluation, recognition accuracies of $99.25\pm 0.14\%$ and $91.51\pm 1.29\%$ are achieved, respectively. Zero-shot performance is assessed by withholding $20\%$ of gesture classes during training and predicting them using only their textual descriptions. In this setting, accuracies of $55.2\pm 12.15\%$ on ArASL2018 and $37.6\pm 9.07\%$ on ArASL21L are obtained. These results show that multimodal vision–language alignment supports semantic transfer and enables recognition of unseen classes. Full article

Text-to-speech (TTS) systems based on neural networks have undergone a significant evolution, taking a step forward towards achieving human-like quality and expressiveness, which is crucial for applications such as social media content creation and voice interfaces for visually impaired individuals. An entire branch of research, known as Expressive Text-to-speech (ETTS), has emerged to address the so-called one-to-many mapping problem, which limits the naturalness of generated output. However, most ETTS systems applying explicit style modeling treat the prediction of prosodic features as a regressive, rather than generative, process and, consequently, do not capture prosodic diversity. We address this problem by proposing a novel technique for inference-time prediction of speaking-style features, which leverages a diffusion framework for sampling from a learned space of Global Style Tokens-based embeddings, which are then used to condition a neural TTS model. By incorporating the diffusion model, we can leverage its powerful modeling capabilities to learn the distribution of possible stylistic features and, during inference, sample them non-deterministically, which makes the generated speech more human-like by alleviating prosodic monotony across multiple sentences. Our system blends a regressive predictor with a diffusion-based generator to enable smooth control over the diversity of generated speech. Through quantitative and qualitative (human-centered) experiments, we demonstrated that our system generates expressive human speech with non-deterministic high-level prosodic features. Full article

To address the challenges of slow synthesis speed, unstable quality, limited emotional expressiveness, and the lack of controllable speaking rate in Mongolian emotional speech synthesis, this paper proposes a speech Rate-Controllable Mongolian emotional speech synthesis model based on improved Tacotron2 (SRC-IT2). First, an end-to-end Mongolian speech synthesis module is constructed based on an improved Tacotron2 framework, incorporating the unique linguistic characteristics of the Mongolian script. The front-end processing is optimized accordingly, and a G2P-Seq2Seq model is employed to achieve accurate grapheme-to-phoneme conversion for Mongolian characters. Next, on top of the end-to-end synthesis framework, a joint text-audio emotion analysis module is integrated to effectively learn and represent emotional style features specific to Mongolian speech. Finally, a style encoder and speaking rate control variable are embedded into the acoustic modeling process, further enhancing Tacotron2’s ability to dynamically adjust the speaking rate during emotional speech generation. Experimental results demonstrate that the proposed model produces more natural-sounding speech with improved emotional expressiveness and enables effective real-time control over speaking rate in Mongolian emotional speech synthesis. Full article

Intuitive eating is an adaptive eating style that could help explain part of the relation between affect and eating behaviors. However, research in this area remains limited. The objectives of this study are twofold. First, we examine the relation between affect, disordered eating attitudes and behaviors (DEABs), and orthorexia nervosa (ON). Second, we investigate the mediating role of intuitive eating regarding these relations. A sample of 197 French-speaking Canadian women, aged from 18 to 69, participated in the study. The results showed that negative affect was related to DEABs and ON, but not positive affect. Statistically significant associations were also found between affect (negative and positive) and the four dimensions of intuitive eating. Additionally, negative relations were found between intuitive eating dimensions and most types of eating behaviors (encompassing DEABs and ON), except for dieting. Finally, our results revealed that the relations between affect (positive and negative) and most types of eating behaviors were indirect (i.e., suggesting mediation) via intuitive eating. Based on these results, it seems that interventions addressing affect regulation and eating behaviors could benefit from including a focus on intuitive eating. Full article

We investigated how participants’ humor styles impact their sarcasm use. English-speaking participants (N = 179) completed online self-report measures of humor styles and sarcasm use. We conducted linear regressions to test whether their humor style scores could predict their sarcasm use scores. Participants with higher affiliative humor scores reported a greater tendency to use sarcasm in general and to use face-saving sarcasm to protect the social images of the speaker and addressee. People use face-saving sarcasm to enhance their relationships, to tease others, and to self-deprecate. Surprisingly, participants who scored high on aggressive humor reported using face-saving sarcasm often. We suspect this occurred because the aggressive humor and the face-saving scales contain conceptually similar items. Participants with high aggressive humor scores also reported frequently using sarcasm to diffuse frustration. Participants who scored high on self-defeating humor reported often using both face-saving sarcasm and sarcasm to diffuse embarrassment. Given that face-saving sarcasm use was uniquely predicted by affiliative humor, aggressive humor, and self-defeating humor scores, we suggest that face-saving sarcasm use has utility for people with a wide range of humor styles. Our findings highlight how an individual’s humor style shapes their flexible use of sarcasm in interpersonal relationships. Full article

Vajrayāna teaching places the guru outside space and time, while simultaneously manifest in the teacher’s physical body. Those who regard Danzanravjaa primarily as a Buddhist teacher even today have his poems as a potent source of his teaching and consequently as a catalyst for their own spiritual development. But what can we hear across two centuries, and how can we actively listen to his religious teaching through his singular, aphoristic, and complex poetics? And to what extent can we understand today his nomadic perspective on Buddhist teaching in order better to understand the particular nature of Mongolian Buddhism? This paper will examine Danzanravjaa’s poetry in both Mongolian and Tibetan through the intertwining outer, inner, and secret levels of Tibeto-Mongolian Vajrayāna Buddhism, listening to how his poetic language and down-to-earth themes might have spoken to his contemporaries, as well as how they might speak to us today. In doing so, it presents Danzanravjaa’s poetry in a different light—not in terms of nineteenth century literature but as actionable spiritual wisdom from a teacher who, like any other, presents his own direct apprehension of Buddha nature in a challenging, personal style. Full article

A significant communication gap persists between the deaf and hearing communities, often leaving deaf individuals isolated and marginalised. This challenge is especially pronounced for Arabic-speaking individuals, given the lack of publicly available Arabic Sign Language datasets and dedicated recognition systems. This study is the first to use the Temporal Convolutional Network (TCN) model for Arabic Sign Language (ArSL) recognition. We created a custom dataset of the 30 most common sentences in ArSL. We improved recognition performance by enhancing a Recurrent Neural Network (RNN) incorporating a Bidirectional Long Short-Term Memory (BiLSTM) model. Our approach achieved outstanding accuracy results compared to baseline RNN-BiLSTM models. This study contributes to developing recognition systems that could bridge communication barriers for the hearing-impaired community. Through a comparative analysis, we assessed the performance of the TCN and the enhanced RNN architecture in capturing the temporal dependencies and semantic nuances unique to Arabic Sign Language. The models are trained and evaluated using the created dataset of Arabic sign gestures based on recognition accuracy, processing speed, and robustness to variations in signing styles. This research provides insights into the strengths and limitations of TCNs and the enhanced RNN-BiLSTM by investigating their applicability in sign language recognition scenarios. The results indicate that the TCN model achieved an accuracy of 99.5%, while the original RNN-BiLSTM model initially achieved a 96% accuracy but improved to 99% after enhancement. While the accuracy gap between the two models was small, the TCN model demonstrated significant advantages in terms of computational efficiency, requiring fewer resources and achieving faster inference times. These factors make TCNs more practical for real-time sign language recognition applications. Full article

Publications on the application of artificial intelligence (AI) to many situations, including those in clinical medicine, created in 2023–2024 are reviewed here. Because of the short time frame covered, here, it is not possible to conduct exhaustive analysis as would be the case in meta-analyses or systematic reviews. Consequently, this literature review presents an examination of narrative AI’s application in relation to contemporary topics related to clinical medicine. The landscape of the findings reviewed here span 254 papers published in 2024 topically reporting on AI in medicine, of which 83 articles are considered in the present review because they contain evidence-based findings. In particular, the types of cases considered deal with AI accuracy in initial differential diagnoses, cancer treatment recommendations, board-style exams, and performance in various clinical tasks, including clinical imaging. Importantly, summaries of the validation techniques used to evaluate AI findings are presented. This review focuses on AIs that have a clinical relevancy evidenced by application and evaluation in clinical publications. This relevancy speaks to both what has been promised and what has been delivered by various AI systems. Readers will be able to understand when generative AI may be expressing views without having the necessary information (ultracrepidarianism) or is responding as if the generative AI had expert knowledge when it does not. A lack of awareness that AIs may deliver inadequate or confabulated information can result in incorrect medical decisions and inappropriate clinical applications (Dunning–Kruger effect). As a result, in certain cases, a generative AI system might underperform and provide results which greatly overestimate any medical or clinical validity. Full article

The COVID-19 pandemic severely affected teaching and student outcomes throughout the world, yet the long-term impacts of the pandemic on teachers and students in Latin America and Spain remain largely underexamined. This study examined the experiences of 5416 teachers from 20 Spanish-speaking countries during and after the pandemic, with an emphasis on teachers’ health, teaching experiences, and school-based support; perceptions of their students’ experiences and struggles; and relationships with students, families, and colleagues. The study used an online survey design with recruitment primarily based on snowball sampling, with most variables being collected using Likert-style responses. Descriptive statistics as well as bivariate correlations between variables were calculated. The results suggested that teachers were mostly healthy and reported moderate fear of COVID-19, though there was much variability. While, on average, teachers did not believe the pandemic had had a negative impact on their relationships with parents, colleagues, and students, they believed that the pandemic had a meaningful negative impact on their students by increasing problems in five key domains: educational, behavioral, social, emotional, and familial. Teachers had received very little training regarding online teaching, although they were moderately satisfied with the resources they had received to teach online and the safety measures their schools had implemented. Schools should provide additional support to teachers, students, and families during times of prolonged stress such as pandemics to help mitigate their lasting effects on students’ academic and psychosocial functioning. Full article

Historically, society has labeled social communication differences in autistic individuals as disordered by comparing them to the social communication behaviors of the predominant non-autistic population. This study explores how autistic young adults view their social communication experiences and how their differences impact them when navigating social situations in predominantly non-autistic environments. This qualitative study utilized purposive sampling to recruit 15 autistic adults aged 18–28 in the United States. All participants were conversation-level speaking communicators and high school graduates. Each participant engaged in an individual semi-structured, conversational interview with the first author via Zoom video conferences between November 2019 and June 2020. The data analysis identified inductive themes through interpretive phenomenological analysis. Five major themes emerged from the data that captured the challenges of autistic adults: (a) “Communication definitely is a struggle at times”, (b) “if it’s a very comfortable situation, then it’s fine”, (c) my communication style has “been very misunderstood”, (d) “I have to learn people”, and (e) “we’re all human. Autistic too, we’re still human”. The participants’ experiences suggest that differences in their communication style and social behavior resulted in overwhelming feelings of uncertainty and marginalization as they put great effort into engaging with non-autistic individuals. Full article

The Preference for Intuition and Deliberation in Food Decision-Making Scale (E-PID) was developed to evaluate both intuitive and deliberative food decision-making within a single instrument. However, its psychometric properties have only been assessed among German-speaking participants. The main aim of the present study was to evaluate evidence of validity and reliability of the E-PID among 604 Brazilian adult women. Exploratory (n = 289) and confirmatory factor analyses (n = 315) were conducted to evaluate the factor structure of the E-PID. Convergent validity was assessed correlating the E-PID with measures of eating behaviors (Tree-Factor Eating Questionnaire-18), intuitive eating (Intuitive Eating Scale-2), and a measure of beliefs and attitudes towards food (Food-Life Questionnaire-SF). McDonald’s Omega coefficient (ω) was used to test the internal consistency of the E-PID. Results from an exploratory and confirmatory factor analysis supported a two-factor structure with seven items. We found good internal consistency (McDonald’s ω = 0.77–0.81). Furthermore, the E-PID demonstrated adequate convergent validity with measures of intuitive, restrictive, emotional and uncontrolled eating, and beliefs and attitudes towards food. Results support the use of the E-PID as a measure of intuition and deliberation in food decision-making among Brazilian adult women, expanding the literature on eating decision-making styles. Full article

This study addresses the critical need for French-language tools in assessing sexual satisfaction, an important aspect of global health, sexual health, and mental health. Its main aim is to validate the French version of the NSSS-SF scale (NSSS-SF Fr, Fr for French). The research was conducted in two phases. The first study involved 253 participants, predominantly female (77.75%), with a focus on examining the tool’s psychometric properties (factorial structure, internal consistency, convergent validity). The second study included 855 participants, with a similar gender distribution, aimed at further validation and analysis, studying links between NSSS-SF Fr and anxiety and depressive symptoms (assessed with GAD7 and MDI), and attachment style (ECR-RS). The NSSS-SF Fr demonstrated robust psychometric properties. Key findings included its strong correlation with sexual health indicators, anxiety, depression, and attachment styles confirming its effectiveness as a reliable tool for evaluating sexual satisfaction in French-speaking populations. Comparisons with international studies highlighted its universal applicability and cultural sensitivity. The NSSS-SF French version stands as a critical tool for future research and clinical practice, bridging a vital gap in the assessment of sexual satisfaction among French-speaking individuals. Full article

This article looks at the Sak Yant tattoo style, which is becoming increasingly popular among so-called “Westerners”. It explores the questions of whether Sak Yant tattoos among “Westerners” will typically fall under copyright issues and cultural appropriation, and what makes Sak Yants relevant to clients. Underlying this research, with a marketing analysis of Sak Yants on Instagram, is the assumption that marketing is also guided by (anticipated) customer desires and can thus tell us something about their perspective. Two interrelated aspects become apparent: Sak Yants integrate aesthetics and spirituality as well as the body and mind, entities that are often considered separately in the “West”, which may be appealing to the “Western” customer and which sets Sak Yants apart from other tattoo styles. The meanings that Sak Yants have usually go deeper than just to the surface, as is not only illustrated by the process and permanence of tattooing but also by the importance of the ritual. People from the respective cultural contexts usually benefit and take part in the process. Therefore, instead of cultural appropriation or appreciation, one could perhaps speak of cultural participation or integration. Full article

Chinookan art centered on the Lower Columbia River and was created by Chinookan-speaking people living along the river and its tributaries. The style is unique, focusing on geometric forms, numerical patterns, and anatomical representation. It is embedded in Chinookan mythology and differs considerably from the more widely recognized Formline of Indigenous artists from the northern Pacific Northwest. It also receives less attention, both publicly and scholarly. Due to high rates of death along the Columbia from introduced diseases during colonial invasion, and high levels of looting that followed, Chinookan art nearly disappeared from the landscape. In the 21st century Chinookan art has had a resurgence, led by Chinookan practitioners. The resurgence occurs not only within individual households but also in public settings. This resurgence also includes an emphasis on teaching the style to youth, who learn that this is not just about making art but is integrally attached to culture more broadly, including connection to language, stories, protocols, and Indigenous identity itself. It is ultimately a source of pride, resilience, and resistance. As a result, where there were once generations who never saw a landscape with Chinookan art, there are now generations who will never know a landscape without it. Full article