Search

Speech disfluency commonly occurs in conversational and spontaneous speech. However, standard Automatic Speech Recognition (ASR) models struggle to accurately recognize these disfluencies because they are typically trained on fluent transcripts. Current research mainly focuses on detecting disfluencies within transcripts, overlooking their exact location and duration in the speech. Additionally, previous work often requires model fine-tuning and addresses limited types of disfluencies. In this work, we present an inference-only approach to augment any ASR model with the ability to detect open-set disfluencies. We first demonstrate that ASR models have difficulty transcribing speech disfluencies. Next, this work proposes a modified Connectionist Temporal Classification(CTC)-based forced alignment algorithm from \cite{kurzinger2020ctc} to predict word-level timestamps while effectively capturing disfluent speech. Additionally, we develop a model to classify alignment gaps between timestamps as either containing disfluent speech or silence. This model achieves an accuracy of 81.62% and an F1-score of 80.07%. We test the augmentation pipeline of alignment gap detection and classification on a disfluent dataset. Our results show that we captured 74.13% of the words that were initially missed by the transcription, demonstrating the potential of this pipeline for downstream tasks., Comment: Accepted by SLT2024

Persuasive social robots employ their social influence to modulate children's behaviours in child-robot interaction. In this work, we introduce the Child-Robot Relational Norm Intervention (CRNI) model, leveraging the passive role of social robots and children's reluctance to inconvenience others to influence children's behaviours. Unlike traditional persuasive strategies that employ robots in active roles, CRNI utilizes an indirect approach by generating a disturbance for the robot in response to improper child behaviours, thereby motivating behaviour change through the avoidance of norm violations. The feasibility of CRNI is explored with a focus on improving children's handwriting posture. To this end, as a preliminary work, we conducted two participatory design workshops with 12 children and 1 teacher to identify effective disturbances that can promote posture correction.

Social robots, owing to their embodied physical presence in human spaces and the ability to directly interact with the users and their environment, have a great potential to support children in various activities in education, healthcare and daily life. Child-Robot Interaction (CRI), as any domain involving children, inevitably faces the major challenge of designing generalized strategies to work with unique, turbulent and very diverse individuals. Addressing this challenging endeavor requires to combine the standpoint of the robot-centered perspective, i.e. what robots technically can and are best positioned to do, with that of the child-centered perspective, i.e. what children may gain from the robot and how the robot should act to best support them in reaching the goals of the interaction. This article aims to help researchers bridge the two perspectives and proposes to address the development of CRI scenarios with insights from child psychology and child development theories. To that end, we review the outcomes of the CRI studies, outline common trends and challenges, and identify two key factors from child psychology that impact child-robot interactions, especially in a long-term perspective: developmental stage and individual characteristics. For both of them we discuss prospective experiment designs which support building naturally engaging and sustainable interactions., Comment: Pre-print submitted to the International Journal of Social Robotics, accepted March 2024

Many countries struggle to effectively introduce Digital Education (DE) to all K-12 students as they lack adequately trained teachers. While cascade models of in-service teacher-professional development (PD) can rapidly deploy PD-programs through multiple levels of trainers to reach all teachers, they suffer from many limitations and are often ineffective. We therefore propose an adapted cascade model to deploy a primary school DE teacher-PD program throughout an administrative region. The model relies on teacher-trainers who (i) are active teachers in the region, (ii) have a prolonged trainer-PD with experts who piloted the teacher-PD program to acquire adult-trainer and DE-related competences, and (iii) are supported by the experts throughout the deployment. To validate the deployment model we used data from 14 teacher-trainers, the 700 teachers they trained, and 350 teachers trained by experts. The teacher-trainer findings demonstrate that the adapted cascade model effectively addresses most cascade models' limitations. The teacher-related findings further validate the adapted cascade model in terms of perception, motivation and adoption which are at least equivalent to those obtained with the experts. To conclude, the adapted cascade model is an effective means of spreading primary school DE PD-programs at a large scale and can be used in other DE reforms.

Early exposure to Computer Science (CS) for all is critical to broaden participation and promote equity in the field. But how does introducting CS into primary school curricula impact learning, perception, and gaps between groups of students? We investigate a CS-curricular reform and teacher Professional Development (PD) program from an equity standpoint by applying hierarchical regression and structural equation modelling on student learning and perception data from three studies with respectively 1384, 2433 & 1644 grade 3-6 students (ages 7-11) and their 83, 142 & 95 teachers. Regarding learning, exposure to CS instruction appears to contribute to closing the performance gap between low-achieving and high-achieving students, as well as pre-existing gender gaps. Despite a lack of direct influence of what was taught on student learning, there is no impact of teachers' demographics or motivation on student learning, with teachers' perception of the CS-PD positively influencing learning. Regarding perception, students perceive CS and its teaching tools (robotics, tablets) positively, and even more so when they perceive a role model close to them as doing CS. Nonetheless gender differences exist all around with boys perceiving CS more positively than girls despite access to CS education. However, access to CS-education affects boys and girls differently: larger gender gaps are closing (namely those related to robotics), while smaller gaps are increasing (namely those related to CS and tablets). To conclude, our findings highlight how a CS curricular reform impacts learning, perception, and equity and supports the importance of i) early introductions to CS for all, ii) preparing teachers to teach CS all the while removing the influence of teacher demographics and motivation on student outcomes, and iii) having developmentally appropriate activities that signal to all groups of students.

The introduction of computing education into curricula worldwide requires multi-year assessments to evaluate the long-term impact on learning. However, no single Computational Thinking (CT) assessment spans primary school, and no group of CT assessments provides a means of transitioning between instruments. This study therefore investigated whether the competent CT test (cCTt) could evaluate learning reliably from grades 3 to 6 (ages 7-11) using data from 2709 students. The psychometric analysis employed Classical Test Theory, Item Response Theory, Measurement Invariance analyses which include Differential Item Functioning, normalised z-scoring, and PISA's methodology to establish proficiency levels. The findings indicate that the cCTt is valid, reliable and gender-fair for grades 3-6, although more complex items would be beneficial for grades 5-6. Grade-specific proficiency levels are provided to help tailor interventions, with a normalised scoring system to compare students across and between grades, and help establish transitions between instruments. To improve the utility of CT assessments among researchers, educators and practitioners, the findings emphasise the importance of i) developing and validating gender-fair, grade-specific, instruments aligned with students' cognitive maturation, and providing ii) proficiency levels, and iii) equivalency scales to transition between assessments. To conclude, the study provides insight into the design of longitudinal developmentally appropriate assessments and interventions., Comment: Accepted, to appear in Technology, Knowledge and Learning

With the increasing importance of Computational Thinking (CT) at all levels of education, it is essential to have valid and reliable assessments. Currently, there is a lack of such assessments in upper primary school. That is why we present the development and validation of the competent CT test (cCTt), an unplugged CT test targeting 7-9 year-old students. In the first phase, 37 experts evaluated the validity of the cCTt through a survey and focus group. In the second phase, the test was administered to 1519 students. We employed Classical Test Theory, Item Response Theory, and Confirmatory Factor Analysis to assess the instruments' psychometric properties. The expert evaluation indicates that the cCTt shows good face, construct, and content validity. Furthermore, the psychometric analysis of the student data demonstrates adequate reliability, difficulty, and discriminability for the target age groups. Finally, shortened variants of the test are established through Confirmatory Factor Analysis. To conclude, the proposed cCTt is a valid and reliable instrument, for use by researchers and educators alike, which expands the portfolio of validated CT assessments across compulsory education. Future assessments looking at capturing CT in a more exhaustive manner might consider combining the cCTt with other forms of assessments., Comment: To appear in the Journal of Educational Computing Research

Research has shown that Educational Robotics (ER) enhances student performance, interest, engagement and collaboration. However, until now, the adoption of robotics in formal education has remained relatively scarce. Among other causes, this is due to the difficulty of determining the alignment of educational robotic learning activities with the learning outcomes envisioned by the curriculum, as well as their integration with traditional, non-robotics learning activities that are well established in teachers' practices. This work investigates the integration of ER into formal mathematics education, through a quasi-experimental study employing the Thymio robot and Scratch programming to teach geometry to two classes of 15-year-old students, for a total of 26 participants. Three research questions were addressed: (1) Should an ER-based theoretical lecture precede, succeed or replace a traditional theoretical lecture? (2) What is the students' perception of and engagement in the ER-based lecture and exercises? (3) Do the findings differ according to students' prior appreciation of mathematics? The results suggest that ER activities are as valid as traditional ones in helping students grasp the relevant theoretical concepts. Robotics activities seem particularly beneficial during exercise sessions: students freely chose to do exercises that included the robot, rated them as significantly more interesting and useful than their traditional counterparts, and expressed their interest in introducing ER in other mathematics lectures. Finally, results were generally consistent between the students that like and did not like mathematics, suggesting the use of robotics as a means to broaden the number of students engaged in the discipline., Comment: To appear in the proceedings of the Sixteenth European Conference on Technology Enhanced Learning (2021)

With the introduction of educational robotics (ER) and computational thinking (CT) in classrooms, there is a rising need for operational models that help ensure that CT skills are adequately developed. One such model is the Creative Computational Problem Solving Model (CCPS) which can be employed to improve the design of ER learning activities. Following the first validation with students, the objective of the present study is to validate the model with teachers, specifically considering how they may employ the model in their own practices. The Utility, Usability and Acceptability framework was leveraged for the evaluation through a survey analysis with 334 teachers. Teachers found the CCPS model useful to foster transversal skills but could not recognise the impact of specific intervention methods on CT-related cognitive processes. Similarly, teachers perceived the model to be usable for activity design and intervention, although felt unsure about how to use it to assess student learning and adapt their teaching accordingly. Finally, the teachers accepted the model, as shown by their intent to replicate the activity in their classrooms, but were less willing to modify it or create their own activities, suggesting that they need time to appropriate the model and underlying tenets., Comment: To appear in the proceedings of the 12th international conference on robotics in education (RiE 2021)

Recently, introducing computer science and educational robots in compulsory education has received increasing attention. However, the use of screens in classrooms is often met with resistance, especially in primary school. To address this issue, this study presents the development of a handwriting-based programming language for educational robots. Aiming to align better with existing classroom practices, it allows students to program a robot by drawing symbols with ordinary pens and paper. Regular smartphones are leveraged to process the hand-drawn instructions using computer vision and machine learning algorithms, and send the commands to the robot for execution. To align with the local computer science curriculum, an appropriate playground and scaffolded learning tasks were designed. The system was evaluated in a preliminary test with eight teachers, developers and educational researchers. While the participants pointed out that some technical aspects could be improved, they also acknowledged the potential of the approach to make computer science education in primary school more accessible., Comment: To appear in the proceedings of the 12th International Conference on Robotics in Education (RiE, 2021)

A dialogue is successful when there is alignment between the speakers at different linguistic levels. In this work, we consider the dialogue occurring between interlocutors engaged in a collaborative learning task, where they are not only evaluated on how well they performed, but also on how much they learnt. The main contribution of this work is to propose new automatic measures to study alignment; focusing on verbal (lexical) alignment, and behavioral alignment (when an instruction given by one was followed with concrete actions by another). A second contribution of our work is to study how spontaneous speech phenomena are used in the process of alignment. Lastly, we make public the dataset to study alignment in educational dialogues. Our results show that all teams verbally and behaviourally align to some degree regardless of their performance and learning, and our measures capture that teams that did not succeed in the task were simply slower to collaborate. Thus we find that teams that performed better, were faster to align. Furthermore, our methodology captures a productive period that includes the time where the interlocutors came up with their best solutions. We also find that well-performing teams verbalise the marker "oh" more when they are behaviourally aligned, compared to other times in the dialogue; showing that this marker is an important cue in alignment. To the best of our knowledge, we are the first to study the role of "oh" as an information management marker in a behavioral context (i.e. in connection to actions taken in a physical environment), compared to only a verbal one. Our measures contribute to the research in the field of educational dialogue and the intersection between dialogue and collaborative learning research., Comment: * The authors contributed equally to this work. This article a preprint under review

Gestures are a natural communication modality for humans. The ability to interpret gestures is fundamental for robots aiming to naturally interact with humans. Wearable sensors are promising to monitor human activity, in particular the usage of triaxial accelerometers for gesture recognition have been explored. Despite this, the state of the art presents lack of systems for reliable online gesture recognition using accelerometer data. The article proposes SLOTH, an architecture for online gesture recognition, based on a wearable triaxial accelerometer, a Recurrent Neural Network (RNN) probabilistic classifier and a procedure for continuous gesture detection, relying on modelling gesture probabilities, that guarantees (i) good recognition results in terms of precision and recall, (ii) immediate system reactivity.

Cultural adaptation, i.e., the matching of a robot's behaviours to the cultural norms and preferences of its user, is a well known key requirement for the success of any assistive application. However, culture-dependent robot behaviours are often implicitly set by designers, thus not allowing for an easy and automatic adaptation to different cultures. This paper presents a method for the design of culture-aware robots, that can automatically adapt their behaviour to conform to a given culture. We propose a mapping from cultural factors to related parameters of robot behaviours which relies on linguistic variables to encode heterogeneous cultural factors in a uniform formalism, and on fuzzy rules to encode qualitative relations among multiple variables. We illustrate the approach in two practical case studies., Comment: Presented at: 2017 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), Naples, Italy, 2017

Cultural competence is a well known requirement for an effective healthcare, widely investigated in the nursing literature. We claim that personal assistive robots should likewise be culturally competent, aware of general cultural characteristics and of the different forms they take in different individuals, and sensitive to cultural differences while perceiving, reasoning, and acting. Drawing inspiration from existing guidelines for culturally competent healthcare and the state-of-the-art in culturally competent robotics, we identify the key robot capabilities which enable culturally competent behaviours and discuss methodologies for their development and evaluation., Comment: Presented at: 26th IEEE International Symposium onRobot and Human Interactive Communication (RO-MAN), 2017, Lisbon, Portugal. arXiv admin note: substantial text overlap with arXiv:1708.06276

Daily life activities, such as eating and sleeping, are deeply influenced by a person's culture, hence generating differences in the way a same activity is performed by individuals belonging to different cultures. We argue that taking cultural information into account can improve the performance of systems for the automated recognition of human activities. We propose four different solutions to the problem and present a system which uses a Naive Bayes model to associate cultural information with semantic information extracted from still images. Preliminary experiments with a dataset of images of individuals lying on the floor, sleeping on a futon and sleeping on a bed suggest that: i) solutions explicitly taking cultural information into account are more accurate than culture-unaware solutions; and ii) the proposed system is a promising starting point for the development of culture-aware Human Activity Recognition methods., Comment: 7 pages, 4 figures, Proc. URAI2017, International Conference on Ubiquitous Robots and Ambient Intelligence, Maison Glad Jeju, Jeju, Korea from June 28-July 2017

Providing elderly and people with special needs, including those suffering from physical disabilities and chronic diseases, with the possibility of retaining their independence at best is one of the most important challenges our society is expected to face. Assistance models based on the home care paradigm are being adopted rapidly in almost all industrialized and emerging countries. Such paradigms hypothesize that it is necessary to ensure that the so-called Activities of Daily Living are correctly and regularly performed by the assisted person to increase the perception of an improved quality of life. This chapter describes the computational inference engine at the core of Arianna, a system able to understand whether an assisted person performs a given set of ADL and to motivate him/her in performing them through a speech-mediated motivational dialogue, using a set of nearables to be installed in an apartment, plus a wearable to be worn or fit in garments.

The nursing literature shows that cultural competence is an important requirement for effective healthcare. We claim that personal assistive robots should likewise be culturally competent, that is, they should be aware of general cultural characteristics and of the different forms they take in different individuals, and take these into account while perceiving, reasoning, and acting. The CARESSES project is an Europe-Japan collaborative effort that aims at designing, developing and evaluating culturally competent assistive robots. These robots will be able to adapt the way they behave, speak and interact to the cultural identity of the person they assist. This paper describes the approach taken in the CARESSES project, its initial steps, and its future plans., Comment: Paper presented at: Ambient Assisted Living, Italian Forum. Genova, Italy, June 12--15, 2017

Providing elderly and people with special needs to retain their independence as long as possible is one of the biggest challenges of the society of tomorrow. Teseo, a startup company spinoff from the University of Genoa, aims at accelerating the transition towards a sustainable healthcare system. Teseo's first concept and product, Arianna, allows for the automated recognition of activities of daily living at home and acts as a wellbeing and healthcare personalized assistant. This abstract outlines the main concepts underlying its features and capabilities., Comment: Paper accepted at the Eight Italian Forum on Ambient Assisted Living (ForItAAL 2017)

Bimanual gestures are of the utmost importance for the study of motor coordination in humans and in everyday activities. A reliable detection of bimanual gestures in unconstrained environments is fundamental for their clinical study and to assess common activities of daily living. This paper investigates techniques for a reliable, unconstrained detection and classification of bimanual gestures. It assumes the availability of inertial data originating from the two hands/arms, builds upon a previously developed technique for gesture modelling based on Gaussian Mixture Modelling (GMM) and Gaussian Mixture Regression (GMR), and compares different modelling and classification techniques, which are based on a number of assumptions inspired by literature about how bimanual gestures are represented and modelled in the brain. Experiments show results related to 5 everyday bimanual activities, which have been selected on the basis of three main parameters: (not) constraining the two hands by a physical tool, (not) requiring a specific sequence of single-hand gestures, being recursive (or not). In the best performing combination of modeling approach and classification technique, five out of five activities are recognized up to an accuracy of 97%, a precision of 82% and a level of recall of 100%., Comment: Submitted to Robotics and Autonomous Systems (Elsevier)

The Industry 4.0 paradigm emphasizes the crucial benefits that collaborative robots, i.e., robots able to work alongside and together with humans, could bring to the whole production process. In this context, an enabling technology yet unreached is the design of flexible robots able to deal at all levels with humans' intrinsic variability, which is not only a necessary element for a comfortable working experience for the person but also a precious capability for efficiently dealing with unexpected events. In this paper, a sensing, representation, planning and control architecture for flexible human-robot cooperation, referred to as FlexHRC, is proposed. FlexHRC relies on wearable sensors for human action recognition, AND/OR graphs for the representation of and reasoning upon cooperation models, and a Task Priority framework to decouple action planning from robot motion planning and control., Comment: Submitted to Mechatronics (Elsevier)