THERADIA: Digital Therapies Augmented by Artificial Intelligence

Tarpin-Bernard, Franck; Fruitet, Joan; Vigne, Jean-Philippe; Constant, Patrick; Chainay, Hanna; Koenig, Olivier; Ringeval, Fabien; Bouchot, Béatrice; Bailly, Gérard; Portet, François; Alisamir, Sina; Zhou, Yongxin; Serre, Jean; Delerue, Vincent; Fournier, Hippolyte; Berenger, Kévin; Zsoldos, Isabella; Perrotin, Olivier; Elisei, Frédéric; Lenglet, Martin; Puaux, Charles; Pacheco, Léo; Fouillen, Mélodie; Ghenassia, Didier

doi:10.1007/978-3-030-80285-1_55

Cited by 4 publications

(7 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These different feedback signals and usages were observed here for task-oriented conversations. Further exploration would be needed to extend and/or complement these observations to other types of dialogues, such as those observed in the context of health care [23].…”

Section: Discussionmentioning

confidence: 96%

Verbal and nonverbal feedback signals in response to increasing levels of miscommunication

Garnier¹,

Ferrand²,

Ringeval³

2023

Interspeech 2023

View full text Add to dashboard Cite

This study aims to explore in detail how listeners respond to communication disruptions in a task-oriented dialogue. We conducted an experiment with participants playing a map task with a partner via a video conferencing system that showed seemingly random breakdowns. In fact, the breakdowns were scripted to induce increasing levels of miscommunication. After an initial interactive session, a second non-interactive session was recorded with one-sided communication from the task leader. Among the fifty or so verbal and nonverbal feedback signals observed, twelve were produced by more than half of the participants. A detailed analysis of their use in different situations, their timing and their co-occurrence, supported that they may have different functions: some appear to be personal reactions of uncertainty, misunderstanding, or inability to complete the task, whereas others were clear repair initiators or turntaking signals deliberately addressed to the interlocutor.

show abstract

Section: Discussionmentioning

confidence: 96%

Verbal and nonverbal feedback signals in response to increasing levels of miscommunication

Garnier¹,

Ferrand²,

Ringeval³

2023

Interspeech 2023

View full text Add to dashboard Cite

show abstract

“…Conversely, a webcam also transmitted the participant's face in real time to the pilot's screen so that the pilot could follow the participant's gaze and movements during the discussions to make them more natural. The videos of the pilot and participant were recorded for later use in the development of the empathic virtual assistant proposed by the THERADIA consortium [42]. The pilot and participant communicated via headsets with integrated microphones, and no audio processing was performed to alter the pilot's voice.…”

Section: Cct and Wizard Of Oz Methodsmentioning

confidence: 99%

“…In the light of these observations, we started the THERADIA (Thérapies Digitales Augmentées par l'Intelligence Artificielle) project in 2020 [42]. This 5-year project aims to develop an empathetic virtual assistant that can accompany users during at-home CCT.…”

Section: Objectivesmentioning

confidence: 99%

“…The virtual assistant must be able to provide adequate emotional support during the session, encouraging and rewarding participants for their efforts, to increase adherence [40]. In this respect, the development of an emotional artificial intelligence that would enable the assistant to detect and automatically adapt to the user's affective states would be particularly useful [42]. To provide a safe environment for patients with cognitive disorders, it is also necessary that the assistant's speech and its interactions with the user are scripted in such a way as to provide a stable and rather predictable framework [40].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

The Value of a Virtual Assistant to Improve Engagement in Computerized Cognitive Training at Home: Exploratory Study

Zsoldos,

Trân,

Fournier

et al. 2024

JMIR Rehabil Assist Technol

Self Cite

View full text Add to dashboard Cite

Background Impaired cognitive function is observed in many pathologies, including neurodegenerative diseases such as Alzheimer disease. At present, the pharmaceutical treatments available to counter cognitive decline have only modest effects, with significant side effects. A nonpharmacological treatment that has received considerable attention is computerized cognitive training (CCT), which aims to maintain or improve cognitive functioning through repeated practice in standardized exercises. CCT allows for more regular and thorough training of cognitive functions directly at home, which represents a significant opportunity to prevent and fight cognitive decline. However, the presence of assistance during training seems to be an important parameter to improve patients’ motivation and adherence to treatment. To compensate for the absence of a therapist during at-home CCT, a relevant option could be to include a virtual assistant to accompany patients throughout their training. Objective The objective of this exploratory study was to evaluate the interest of including a virtual assistant to accompany patients during CCT. We investigated the relationship between various individual factors (eg, age, psycho-affective functioning, personality, personal motivations, and cognitive skills) and the appreciation and usefulness of a virtual assistant during CCT. This study is part of the THERADIA (Thérapies Digitales Augmentées par l’Intelligence Artificielle) project, which aims to develop an empathetic virtual assistant. Methods A total of 104 participants were recruited, including 52 (50%) young adults (mean age 21.2, range 18 to 27, SD 2.9 years) and 52 (50%) older adults (mean age 67.9, range 60 to 79, SD 5.1 years). All participants were invited to the laboratory to answer several questionnaires and perform 1 CCT session, which consisted of 4 cognitive exercises supervised by a virtual assistant animated by a human pilot via the Wizard of Oz method. The participants evaluated the virtual assistant and CCT at the end of the session. Results Analyses were performed using the Bayesian framework. The results suggest that the virtual assistant was appreciated and perceived as useful during CCT in both age groups. However, older adults rated the assistant and CCT more positively overall than young adults. Certain characteristics of users, especially their current affective state (ie, arousal, intrinsic relevance, goal conduciveness, and anxiety state), appeared to be related to their evaluation of the session. Conclusions This study provides, for the first time, insight into how young and older adults perceive a virtual assistant during CCT. The results suggest that such an assistant could have a beneficial influence on users’ motivation, provided that it can handle different situations, particularly their emotional state. The next step of our project will be to evaluate our device with patients experiencing mild cognitive impairment and to test its effectiveness in long-term cognitive training.

show abstract

“…Sentences that were not uttered with a specific style were labeled as "Narrative". This audiovisual expressive dataset was recorded in the GIPSA-Lab, as part of the Theradia project [20]. The 12 styles were chosen to cover the expressive needs of the Theradia application.…”

Section: Models and Datasetmentioning

confidence: 99%

Local Style Tokens: Fine-Grained Prosodic Representations For TTS Expressive Control

Lenglet,

Perrotin,

Bailly

2023

12th ISCA Speech Synthesis Workshop (SSW2023)

View full text Add to dashboard Cite

Neural Text-To-Speech (TTS) models achieve great performances regarding naturalness, but modeling expressivity remains an ongoing challenge. Some success was found through implicit approaches like Global Style Tokens (GST), but these methods model speech style at utterance-level. In this paper, we propose to add an auxiliary module called Local Style Tokens (LST) in the encoder-decoder pipeline to model local variations in prosody. This module can implement various scales of representations; we chose Word-level and Phoneme-level prosodic representations to assess the capabilities of the proposed module to better model sub-utterance style variations. Objective evaluation of the synthetic speech shows that LST modules better capture prosodic variations on 12 common styles compared to a GST baseline. These results were validated by participants during listening tests.

show abstract

THERADIA: Digital Therapies Augmented by Artificial Intelligence

Cited by 4 publications

References 23 publications

Verbal and nonverbal feedback signals in response to increasing levels of miscommunication

Verbal and nonverbal feedback signals in response to increasing levels of miscommunication

The Value of a Virtual Assistant to Improve Engagement in Computerized Cognitive Training at Home: Exploratory Study

Local Style Tokens: Fine-Grained Prosodic Representations For TTS Expressive Control

Contact Info

Product

Resources

About