Archivio della ricerca - Fondazione Bruno Kessler
Not a member yet
21227 research outputs found
Sort by
Speech LLMs in Low-Resource Scenarios: Data Volume Requirements and the Impact of Pretraining on High-Resource Languages
Get PDFLarge language models (LLMs) have demonstrated potential in handling spoken inputs for high-resource languages, reaching state-of-the-art performance in various tasks. However, their applicability is still less explored in low-resource settings. This work investigates the use of Speech LLMs for lowresource Automatic Speech Recognition using the SLAM-ASR framework, where a trainable lightweight projector connects a speech encoder and a LLM. Firstly, we assess training data volume requirements to match Whisper-only performance, reemphasizing the challenges of limited data. Secondly, we show that leveraging mono- or multilingual projectors pretrained on high-resource languages reduces the impact of data scarcity, especially with small training sets. Using multilingual LLMs (EuroLLM, Salamandra) with whisper-large-v3-turbo, we evaluate performance on several public benchmarks, providing insights for future research on optimizing Speech LLMs for lowresource languages and multilinguality
Prevention of postpartum depression via a digital acceptance and commitment therapy-based intervention: protocol for a pilot usability study
Get PDFIntroduction: The perinatal period — encompassing pregnancy and the first months after childbirth — is a time of increased psychological vulnerability. It is often associated with high levels of anxiety, stress and depression. Access to psychological support is frequently limited by stigma, geographical barriers, and a shortage of services. Digital health interventions offer promising solutions to overcome these obstacles.
Methods: This study evaluates the acceptability, feasibility, and user experience of REA, a virtual coach based on Acceptance and Commitment Therapy (ACT), to promote psychological well−being and prevent postpartum depression (PPD). Fifty pregnant women (25–30 weeks of gestation) will be recruited. The 8−week intervention delivers psychoeducational content via text, audio, and video, and collects steps, sleep, and heart rate via smartwatches for triangulation with self−reported measures. User Experience (UX) and User Engagement (UE) will be assessed with the System Usability Scale (SUS), the User Engagement Scale–Short Form (UES−SF), the Italian Chatbot Usability Scale, version B (ITA BUS B), and the User Version of the Mobile Application Rating Scale (uMARS), alongside semi−structured interviews. Psychological outcomes will be assessed pre–post with the two Whooley Questions, the Center for Epidemiological Studies Depression Scale (CES−D), the Multidimensional Psychological Flexibility Inventory (MPFI), and the 12−Item Short Form Health Survey (SF−12).
Expected results: The intervention is expected to demonstrate high levels of user satisfaction and engagement (SUS ≥ 68, UES-SF ≥ 3,5/5; ITA BUS B ≥ 44/55 (≈4,0/5); uMARS ≥ 4,0/5), resulting in improvements in psychological flexibility, perceived well-being, and overall quality of life, recognizing that preventive efficacy will be evaluated in subsequent studies with controlled designs and postpartum outcome measures.
Discussion: REA represents a scalable and accessible tool to support perinatal mental health, offering an innovative approach to the early prevention of postpartum distress.
Trial registration: This study was approved by the ethics committee of the APSS (Provincial Health Services Authority) under number 12090 (May 15, 2025)
Altruistic ageing: how age inequality contributes to care work’s construction as a burden
No full textTime can invalidate algorithmic recourse
No full textAlgorithmic Recourse (AR) aims to provide users with actionable steps to overturn unfavourable decisions made by machine learning predictors. However, these actions often take time to implement (e.g., getting a degree can take years), and their effects may vary as the world evolves. Thus, it is natural to ask for recourse that remains valid in a dynamic environment. In this paper, we study the robustness of algorithmic recourse over time by casting the problem through the lens of causality. We demonstrate theoretically and empirically that (even robust) causal AR methods can fail over time except in the – unlikely – case that the world is stationary. Even more critically, unless the world is fully deterministic, counterfactual AR cannot be solved optimally. To account for this, we propose a simple yet effective algorithm for temporal AR that explicitly accounts for time under the assumption of having access to an estimator approximating the stochastic process. Our simulations on synthetic and realistic datasets show how considering time produces more resilient solutions to potential trends in the data distribution
Measurement of jet track functions in pp collisions at √s = 13 TeV with the ATLAS detector
No full textMeasurements of jet substructure are key to probing the energy frontier at colliders, and many of them use track-based observables which take advantage of the angular precision of tracking detectors. Theoretical calculations of track-based observables require ‘track functions’, which characterize the transverse momentum fraction carried by charged hadrons from a fragmenting quark or gluon. This letter presents a direct measurement of distributions in dijet events from the 140 fb−1 of proton–proton collisions at TeV recorded with the ATLAS detector. The data are corrected for detector effects using machine-learning methods. The scale evolution of the moments of the distribution is sensitive to non-linear renormalization group evolution equations of QCD, and is compared with analytic predictions. When incorporated into future theoretical calculations, these results will enable a precision program of theory-data comparison for track-based jet substructure observables
Job loss disrupts individuals’ mobility and their exploratory patterns
No full textIn recent years, human mobility research has discovered universal patterns capable of describing how people move. These regularities have been shown to partly depend on individual and environmental characteristics (e.g., gender, rural/urban, and country). In this work, we show that life-course events, such as job loss, can disrupt individual mobility patterns. Adversely affecting individuals’ well-being and potentially increasing the risk of social and economic inequalities, we show that job loss drives a significant change in the exploratory behavior of individuals with changes that intensify over time since the job loss. Our findings shed light on the dynamics of employment-related behavior at scale, providing a deeper understanding of key components in human mobility regularities. These drivers can facilitate targeted social interventions to support the most vulnerable populations
