@article{delangle_speaking_2026,

title = {Speaking face-to-face with a virtual avatar to reduce anxiety in students who stutter: Tool development and pilot study results},

author = {M. Delangle and A. Moïse-Richard and A. -L. Leclercq and D. Labbé and S. Bouchard and S. Andrews and L. Ménard},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-105028302364&doi=10.1016%2Fj.jfludis.2026.106194&partnerID=40&md5=af0d246f9187ee19796f36456887400b},

doi = {10.1016/j.jfludis.2026.106194},

issn = {0094730X (ISSN)},

year  = {2026},

date = {2026-01-01},

journal = {Journal of Fluency Disorders},

volume = {87},

abstract = {Purpose Speaking in class is challenging for students who stutter. Cognitive-behavioral therapy (CBT) with exposure in virtual reality (VR) emerges as a promising intervention for treating speaking anxiety in pediatric populations. This pilot study tested if real-time avatar-based VR can elicit anxiety responses while remaining acceptable to youth who stutter. Method Twelve students who stutter (aged 9–18) were randomly assigned to a single training session conducted either (1) in VR with a realistic avatar controlled live by their SLP, or (2) in role-play with their SLP, before facing a real actor. We assessed system acceptability, anxiety levels and perceived self-efficacy. Results The VR system was well accepted and elicited physiological arousal comparable to real-life interactions. Although participants reported experiencing less anxiety during VR, skin conductance level showed higher arousal; suggesting a divergence between the subjective report and physiological response. Finally, one training session (either in VR or with the SLP) did not produce gains in self-efficacy or decrease in anxiety related to the final real-actor conversation. Conclusion This study demonstrates evidence that the potential use of immersive VR could represent an acceptable and viable complementary strategy for SLP treatment, that could control exposure parameters while evoking physiological responses similar to real-life contexts. The differences between subjective and physiological measures suggest that VR is inducing anxiety responses differently than it was perceived. Further research could investigate the use of VR as anxiety interventions for students who stutter and should be explored across multi-session studies to understand their therapeutic effect. © 2026 The Authors.},

keywords = {Adolescent, adult, Anxiety, Arousal, article, Avatar, avoidance behavior, Canada, Child, clinical article, cognitive behavioral therapy, complication, controlled study, distance learning, ecological validity, electrocardiogram, electrodermal response, exposure, female, Heart Rate, heart rate variability, human, Humans, Liebowitz Social Anxiety Scale, Likert scale, male, nonverbal communication, physiological stress, Pilot Projects, pilot study, procedures, psychology, questionnaire, randomized controlled trial, role playing, School-age children, Self Concept, Self Efficacy, self report, Signal processing, skin conductance, social anxiety, speech, student, Students, Stuttering, Therapy, treatment outcome, virtual reality, virtual reality exposure therapy},

pubstate = {published},

tppubtype = {article}

}

@article{delangleSpeakingFacetofaceVirtual2026,

title = {Speaking face-to-face with a virtual avatar to reduce anxiety in students who stutter: Tool development and pilot study results},

author = {M. Delangle and A. Moïse-Richard and A. -L. Leclercq and D. Labbé and S. Bouchard and S. Andrews and L. Ménard},

url = {https://www.scopus.com/pages/publications/105028302364?origin=resultslist},

doi = {10.1016/j.jfludis.2026.106194},

issn = {0094730X (ISSN)},

year  = {2026},

date = {2026-01-01},

journal = {Journal of Fluency Disorders},

volume = {87},

publisher = {Elsevier Inc.},

abstract = {Purpose Speaking in class is challenging for students who stutter. Cognitive-behavioral therapy (CBT) with exposure in virtual reality (VR) emerges as a promising intervention for treating speaking anxiety in pediatric populations. This pilot study tested if real-time avatar-based VR can elicit anxiety responses while remaining acceptable to youth who stutter. Method Twelve students who stutter (aged 9–18) were randomly assigned to a single training session conducted either (1) in VR with a realistic avatar controlled live by their SLP, or (2) in role-play with their SLP, before facing a real actor. We assessed system acceptability, anxiety levels and perceived self-efficacy. Results The VR system was well accepted and elicited physiological arousal comparable to real-life interactions. Although participants reported experiencing less anxiety during VR, skin conductance level showed higher arousal; suggesting a divergence between the subjective report and physiological response. Finally, one training session (either in VR or with the SLP) did not produce gains in self-efficacy or decrease in anxiety related to the final real-actor conversation. Conclusion This study demonstrates evidence that the potential use of immersive VR could represent an acceptable and viable complementary strategy for SLP treatment, that could control exposure parameters while evoking physiological responses similar to real-life contexts. The differences between subjective and physiological measures suggest that VR is inducing anxiety responses differently than it was perceived. Further research could investigate the use of VR as anxiety interventions for students who stutter and should be explored across multi-session studies to understand their therapeutic effect. © 2026 The Authors.},

keywords = {Adolescent, adult, Anxiety, Arousal, article, Avatar, avoidance behavior, Canada, Child, clinical article, cognitive behavioral therapy, complication, controlled study, distance learning, ecological validity, electrocardiogram, electrodermal response, exposure, female, Heart Rate, heart rate variability, human, Humans, Liebowitz Social Anxiety Scale, Likert scale, male, nonverbal communication, physiological stress, Pilot Projects, pilot study, procedures, psychology, questionnaire, randomized controlled trial, role playing, School-age children, Self Concept, Self Efficacy, self report, Signal processing, skin conductance, social anxiety, speech, student, Students, Stuttering, Therapy, treatment outcome, virtual reality, virtual reality exposure therapy},

pubstate = {published},

tppubtype = {article}

}

@article{delangleSpeakingFacetofaceVirtual2026a,

title = {Speaking face-to-face with a virtual avatar to reduce anxiety in students who stutter: Tool development and pilot study results},

author = {M. Delangle and A. Moïse-Richard and A. -L. Leclercq and D. Labbé and S. Bouchard and S. Andrews and L. Ménard},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-105028302364&doi=10.1016%2Fj.jfludis.2026.106194&partnerID=40&md5=af0d246f9187ee19796f36456887400b},

doi = {10.1016/j.jfludis.2026.106194},

issn = {0094730X (ISSN)},

year  = {2026},

date = {2026-01-01},

journal = {Journal of Fluency Disorders},

volume = {87},

abstract = {Purpose Speaking in class is challenging for students who stutter. Cognitive-behavioral therapy (CBT) with exposure in virtual reality (VR) emerges as a promising intervention for treating speaking anxiety in pediatric populations. This pilot study tested if real-time avatar-based VR can elicit anxiety responses while remaining acceptable to youth who stutter. Method Twelve students who stutter (aged 9–18) were randomly assigned to a single training session conducted either (1) in VR with a realistic avatar controlled live by their SLP, or (2) in role-play with their SLP, before facing a real actor. We assessed system acceptability, anxiety levels and perceived self-efficacy. Results The VR system was well accepted and elicited physiological arousal comparable to real-life interactions. Although participants reported experiencing less anxiety during VR, skin conductance level showed higher arousal; suggesting a divergence between the subjective report and physiological response. Finally, one training session (either in VR or with the SLP) did not produce gains in self-efficacy or decrease in anxiety related to the final real-actor conversation. Conclusion This study demonstrates evidence that the potential use of immersive VR could represent an acceptable and viable complementary strategy for SLP treatment, that could control exposure parameters while evoking physiological responses similar to real-life contexts. The differences between subjective and physiological measures suggest that VR is inducing anxiety responses differently than it was perceived. Further research could investigate the use of VR as anxiety interventions for students who stutter and should be explored across multi-session studies to understand their therapeutic effect. © 2026 The Authors.},

keywords = {Adolescent, adult, Anxiety, Arousal, article, Avatar, avoidance behavior, Canada, Child, clinical article, cognitive behavioral therapy, complication, controlled study, distance learning, ecological validity, electrocardiogram, electrodermal response, exposure, female, Heart Rate, heart rate variability, human, Humans, Liebowitz Social Anxiety Scale, Likert scale, male, nonverbal communication, physiological stress, Pilot Projects, pilot study, procedures, psychology, questionnaire, randomized controlled trial, role playing, School-age children, Self Concept, Self Efficacy, self report, Signal processing, skin conductance, social anxiety, speech, student, Students, Stuttering, Therapy, treatment outcome, virtual reality, virtual reality exposure therapy},

pubstate = {published},

tppubtype = {article}

}

@article{joudeh_predicting_2024,

title = {Predicting the Arousal and Valence Values of Emotional States Using Learned, Predesigned, and Deep Visual Features †},

author = {I. O. Joudeh and A. -M. Cretu and S. Bouchard},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85198382238&doi=10.3390%2fs24134398&partnerID=40&md5=cefa8b2e2c044d02f99662af350007db},

doi = {10.3390/s24134398},

issn = {14248220 (ISSN)},

year  = {2024},

date = {2024-01-01},

journal = {Sensors},

volume = {24},

number = {13},

publisher = {Multidisciplinary Digital Publishing Institute (MDPI)},

abstract = {The cognitive state of a person can be categorized using the circumplex model of emotional states, a continuous model of two dimensions: arousal and valence. The purpose of this research is to select a machine learning model(s) to be integrated into a virtual reality (VR) system that runs cognitive remediation exercises for people with mental health disorders. As such, the prediction of emotional states is essential to customize treatments for those individuals. We exploit the Remote Collaborative and Affective Interactions (RECOLA) database to predict arousal and valence values using machine learning techniques. RECOLA includes audio, video, and physiological recordings of interactions between human participants. To allow learners to focus on the most relevant data, features are extracted from raw data. Such features can be predesigned, learned, or extracted implicitly using deep learners. Our previous work on video recordings focused on predesigned and learned visual features. In this paper, we extend our work onto deep visual features. Our deep visual features are extracted using the MobileNet-v2 convolutional neural network (CNN) that we previously trained on RECOLA’s video frames of full/half faces. As the final purpose of our work is to integrate our solution into a practical VR application using head-mounted displays, we experimented with half faces as a proof of concept. The extracted deep features were then used to predict arousal and valence values via optimizable ensemble regression. We also fused the extracted visual features with the predesigned visual features and predicted arousal and valence values using the combined feature set. In an attempt to enhance our prediction performance, we further fused the predictions of the optimizable ensemble model with the predictions of the MobileNet-v2 model. After decision fusion, we achieved a root mean squared error (RMSE) of 0.1140, a Pearson’s correlation coefficient (PCC) of 0.8000, and a concordance correlation coefficient (CCC) of 0.7868 on arousal predictions. We achieved an RMSE of 0.0790, a PCC of 0.7904, and a CCC of 0.7645 on valence predictions. © 2024 by the authors.},

note = {Publisher: Multidisciplinary Digital Publishing Institute (MDPI)},

keywords = {adult, Affective interaction, Arousal, artificial neural network, Cognitive state, Cognitive/emotional state, Collaborative interaction, computer, Convolutional neural networks, correlation coefficient, Deep learning, emotion, Emotional state, Emotions, female, Forecasting, Helmet mounted displays, human, Humans, Learning algorithms, Learning systems, Long short-term memory, Machine learning, Machine-learning, male, Mean square error, Neural networks, physiology, Regression, Root mean squared errors, Video recording, virtual reality, Visual feature, visual features},

pubstate = {published},

tppubtype = {article}

}

@article{joudehPredictingArousalValence2024,

title = {Predicting the Arousal and Valence Values of Emotional States Using Learned, Predesigned, and Deep Visual Features †},

author = {I. O. Joudeh and A. -M. Cretu and S. Bouchard},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85198382238&doi=10.3390%2fs24134398&partnerID=40&md5=cefa8b2e2c044d02f99662af350007db},

doi = {10.3390/s24134398},

issn = {14248220 (ISSN)},

year  = {2024},

date = {2024-01-01},

journal = {Sensors},

volume = {24},

number = {13},

publisher = {Multidisciplinary Digital Publishing Institute (MDPI)},

abstract = {The cognitive state of a person can be categorized using the circumplex model of emotional states, a continuous model of two dimensions: arousal and valence. The purpose of this research is to select a machine learning model(s) to be integrated into a virtual reality (VR) system that runs cognitive remediation exercises for people with mental health disorders. As such, the prediction of emotional states is essential to customize treatments for those individuals. We exploit the Remote Collaborative and Affective Interactions (RECOLA) database to predict arousal and valence values using machine learning techniques. RECOLA includes audio, video, and physiological recordings of interactions between human participants. To allow learners to focus on the most relevant data, features are extracted from raw data. Such features can be predesigned, learned, or extracted implicitly using deep learners. Our previous work on video recordings focused on predesigned and learned visual features. In this paper, we extend our work onto deep visual features. Our deep visual features are extracted using the MobileNet-v2 convolutional neural network (CNN) that we previously trained on RECOLA’s video frames of full/half faces. As the final purpose of our work is to integrate our solution into a practical VR application using head-mounted displays, we experimented with half faces as a proof of concept. The extracted deep features were then used to predict arousal and valence values via optimizable ensemble regression. We also fused the extracted visual features with the predesigned visual features and predicted arousal and valence values using the combined feature set. In an attempt to enhance our prediction performance, we further fused the predictions of the optimizable ensemble model with the predictions of the MobileNet-v2 model. After decision fusion, we achieved a root mean squared error (RMSE) of 0.1140, a Pearson’s correlation coefficient (PCC) of 0.8000, and a concordance correlation coefficient (CCC) of 0.7868 on arousal predictions. We achieved an RMSE of 0.0790, a PCC of 0.7904, and a CCC of 0.7645 on valence predictions. © 2024 by the authors.},

keywords = {adult, Affective interaction, Arousal, artificial neural network, Cognitive state, Cognitive/emotional state, Collaborative interaction, computer, Convolutional neural networks, correlation coefficient, Deep learning, emotion, Emotional state, Emotions, female, Forecasting, Helmet mounted displays, human, Humans, Learning algorithms, Learning systems, Long short-term memory, Machine learning, Machine-learning, male, Mean square error, Neural networks, physiology, Regression, Root mean squared errors, Video recording, virtual reality, Visual feature, visual features},

pubstate = {published},

tppubtype = {article}

}

@article{joudeh_prediction_2023,

title = {Prediction of Emotional States from Partial Facial Features for Virtual Reality Applications},

author = {I. O. Joudeh and A. -M. Cretu and S. Bouchard and S. Guimond},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85182471413&partnerID=40&md5=8190e0dbb5b48ae508515f4029b0a0d1},

doi = {10.3390/s23125613},

issn = {15548716},

year  = {2023},

date = {2023-01-01},

journal = {Annual Review of CyberTherapy and Telemedicine},

volume = {21},

number = {12},

pages = {17–21},

publisher = {Interactive Media Institute},

abstract = {The availability of virtual reality (VR) in numerous clinical contexts has been made possible by recent technological advancements. One application is using VR for cognitive interventions with individuals who have mental disorders. Predicting the emotional states of users could help to prevent their discouragement during VR interventions. We can monitor the emotional states of individuals using sensors like an external camera, as they engage in various tasks within VR environments. The emotional state of VR users can be measured through arousal and valence, as per the Circumplex model. We used the Remote Collaborative and Affective Interactions (RECOLA) database of emotional behaviours. We processed video frames from 18 RECOLA videos. Due to the headset in VR systems, we detected faces and cropped the images of faces to use the lower half of the face only. We labeled the images with arousal and valence values to reflect various emotions. Convolutional neural networks (CNNs), specifically MobileNet-v2 and ResNets-18, were then used to predict arousal and valence values. MobileNet-v2 outperforms ResNet-18 as well as others from the literature. We achieved a root mean squared error (RMSE), Pearson’s correlation coefficient (PCC), and Concordance correlation coefficient (CCC) of 0.1495, 0.6387, and 0.6081 for arousal, and 0.0996, 0.6453, and 0.6232 for valence. Our work acts as a proof-of-concept for predicting emotional states from arousal and valence values via visual data of users immersed in VR experiences. In the future, predicted emotions could be used to automatically adjust the VR environment for individuals engaged in cognitive interventions. © 2023, Interactive Media Institute. All rights reserved.},

note = {Publisher: MDPI},

keywords = {Arousal, article, clinical article, convolutional neural network, correlation coefficient, data base, emotion, facies, female, human, human experiment, Image processing, long short term memory network, male, random forest, residual neural network, root mean squared error, videorecording, virtual reality},

pubstate = {published},

tppubtype = {article}

}

@article{joudeh_prediction_2023-1,

title = {Prediction of Continuous Emotional Measures through Physiological and Visual Data †},

author = {I. O. Joudeh and A. -M. Cretu and S. Bouchard and S. Guimond},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85163943735&doi=10.3390%2fs23125613&partnerID=40&md5=5e970f0d8c5790b85d8d77a9f3f52a2d},

doi = {10.3390/s23125613},

issn = {14248220},

year  = {2023},

date = {2023-01-01},

journal = {Sensors},

volume = {23},

number = {12},

pages = {17–21},

publisher = {MDPI},

abstract = {The affective state of a person can be measured using arousal and valence values. In this article, we contribute to the prediction of arousal and valence values from various data sources. Our goal is to later use such predictive models to adaptively adjust virtual reality (VR) environments and help facilitate cognitive remediation exercises for users with mental health disorders, such as schizophrenia, while avoiding discouragement. Building on our previous work on physiological, electrodermal activity (EDA) and electrocardiogram (ECG) recordings, we propose improving preprocessing and adding novel feature selection and decision fusion processes. We use video recordings as an additional data source for predicting affective states. We implement an innovative solution based on a combination of machine learning models alongside a series of preprocessing steps. We test our approach on RECOLA, a publicly available dataset. The best results are obtained with a concordance correlation coefficient (CCC) of 0.996 for arousal and 0.998 for valence using physiological data. Related work in the literature reported lower CCCs on the same data modality; thus, our approach outperforms the state-of-the-art approaches for RECOLA. Our study underscores the potential of using advanced machine learning techniques with diverse data sources to enhance the personalization of VR environments. © 2023 by the authors.},

note = {Publisher: Interactive Media Institute},

keywords = {Affect recognition, Affective state, Arousal, Data-source, Deep learning, Electrocardiography, emotion, Emotion Recognition, Emotions, face recognition, Faces detection, Forecasting, human, Humans, Images processing, Learning systems, Machine learning, Machine-learning, mental disease, Mental Disorders, Physiological data, physiology, Signal-processing, Statistical tests, Video recording, Virtual-reality environment},

pubstate = {published},

tppubtype = {article}

}

@article{tremblay_development_2013,

title = {The development of a haptic virtual reality environment to study body image and affect},

author = {L. Tremblay and S. Bouchard and B. Chebbi and L. Wei and J. Monthuy-Blanc and D. Boulanger},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-84894231106&partnerID=40&md5=79731f3a31e9e70fcf3bf8f5db1f7d7c},

issn = {15548716},

year  = {2013},

date = {2013-01-01},

journal = {Annual Review of CyberTherapy and Telemedicine},

volume = {11},

pages = {80–84},

publisher = {Virtual reality med institute},

abstract = {We report the results of a preliminary study testing the effect of participants’ mood rating on visual motor performance using a haptic device to manipulate a cartoonish human body. Our results suggest that moods involving high arousal (e.g. happiness) produce larger movements whereas mood involving low arousal (e.g. sadness) produce slower speed of performance. Our results are used for the development of a new haptic virtual reality application that we briefly present here. This application is intended to create a more interactive and motivational environment to treat body image issues and for emotional communication. © 2013 Interactive Media Institute.},

note = {Publisher: Virtual reality med institute},

keywords = {Affect, Arousal, art, article, Biofeedback, body image, computer interface, Emotional communications, female, happiness, Haptic devices, Haptics, human, Human bodies, human experiment, Humans, male, methodology, Mood, motor performance, physiology, psychological aspect, psychology, Psychomotor Performance, Psychophysiology, sadness, Touch, User-Computer Interface, velocity, virtual reality, Virtual-reality environment, Young Adult},

pubstate = {published},

tppubtype = {article}

}

@article{tremblayDevelopmentHapticVirtual2013,

title = {The development of a haptic virtual reality environment to study body image and affect},

author = {L. Tremblay and S. Bouchard and B. Chebbi and L. Wei and J. Monthuy-Blanc and D. Boulanger},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-84894231106&partnerID=40&md5=79731f3a31e9e70fcf3bf8f5db1f7d7c},

issn = {15548716},

year  = {2013},

date = {2013-01-01},

journal = {Annual Review of CyberTherapy and Telemedicine},

volume = {11},

pages = {80–84},

publisher = {Virtual reality med institute},

abstract = {We report the results of a preliminary study testing the effect of participants’ mood rating on visual motor performance using a haptic device to manipulate a cartoonish human body. Our results suggest that moods involving high arousal (e.g. happiness) produce larger movements whereas mood involving low arousal (e.g. sadness) produce slower speed of performance. Our results are used for the development of a new haptic virtual reality application that we briefly present here. This application is intended to create a more interactive and motivational environment to treat body image issues and for emotional communication. © 2013 Interactive Media Institute.},

keywords = {Affect, Arousal, art, article, Biofeedback, body image, computer interface, Emotional communications, female, happiness, Haptic devices, Haptics, human, Human bodies, human experiment, Humans, male, methodology, Mood, motor performance, physiology, psychological aspect, psychology, Psychomotor Performance, Psychophysiology, sadness, Touch, User-Computer Interface, velocity, virtual reality, Virtual-reality environment, Young Adult},

pubstate = {published},

tppubtype = {article}

}

@article{bouchard_using_2012,

title = {Using biofeedback while immersed in a stressful videogame increases the effectiveness of stress management skills in soldiers},

author = {S. Bouchard and F. Bernier and E. Boivin and B. Morin and G. Robillard},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-84860485827&doi=10.1371%2fjournal.pone.0036169&partnerID=40&md5=4b29a984169d2fe12d54f4c562344723},

doi = {10.1371/journal.pone.0036169},

issn = {19326203},

year  = {2012},

date = {2012-01-01},

journal = {PLoS ONE},

volume = {7},

number = {4},

abstract = {This study assessed the efficacy of using visual and auditory biofeedback while immersed in a tridimensional videogame to practice a stress management skill (tactical breathing). All 41 participants were soldiers who had previously received basic stress management training and first aid training in combat. On the first day, they received a 15-minute refresher briefing and were randomly assigned to either: (a) no additional stress management training (SMT) for three days, or (b) 30-minute sessions (one per day for three days) of biofeedback-assisted SMT while immersed in a horror/first-person shooter game. The training was performed in a dark and enclosed environment using a 50-inch television with active stereoscopic display and loudspeakers. On the last day, all participants underwent a live simulated ambush with an improvised explosive device, where they had to provide first aid to a wounded soldier. Stress levels were measured with salivary cortisol collected when waking-up, before and after the live simulation. Stress was also measured with heart rate at baseline, during an apprehension phase, and during the live simulation. Repeated-measure ANOVAs and ANCOVAs confirmed that practicing SMT was effective in reducing stress. Results are discussed in terms of the advantages of the proposed program for military personnel and the need to practice SMT. © 2012 Bouchard et al.},

keywords = {adult, Arousal, article, Biofeedback, clinical trial, controlled clinical trial, controlled study, explosion, feedback system, first aid, Heart Rate, human, human experiment, Humans, Hydrocortisone, male, mental stress, metabolism, methodology, Military Personnel, military phenomena, normal human, pathophysiology, Psychological, psychological aspect, psychology, Psychophysiology, randomized controlled trial, recreation, Saliva, saliva level, simulation, soldier, Stress, Stress management, Video Games},

pubstate = {published},

tppubtype = {article}

}