arxiv: 2604.16408 · v1 · submitted 2026-04-01 · 💻 cs.RO · cs.HC

Recognition: no theorem link

An Edge-Host-Cloud Architecture for Robot-Agnostic, Caregiver-in-the-Loop Personalized Cognitive Exercise: Multi-Site Deployment in Dementia Care

Fengpei Yuan, Ruth Palan Lopez, Shu Fen Wung, Wenzheng Zhao

Authors on Pith no claims yet

Pith reviewed 2026-05-13 22:57 UTC · model grok-4.3

classification 💻 cs.RO cs.HC

keywords dementia carerobotic interactionedge computingpersonalized dialoguecaregiver involvementcognitive exercisemultimodal systemsprivacy-preserving AI

0 comments

The pith

Speaking Memories delivers personalized dementia cognitive exercises through a robot-agnostic edge-host-cloud system that incorporates caregiver biographical knowledge and achieves sub-6-second latency.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper introduces Speaking Memories as a distributed platform that combines caregiver input via a secure cloud portal with local edge processing and various robotic embodiments for cognitive exercise support in dementia care. It fuses auditory, visual, and textual signals to create emotion-aware dialogues while keeping robot hardware decoupled from the core multimodal reasoning and perception functions. Real-world multi-site deployments confirm low-latency operation, stable interactions, and positive feedback from both participants and caregivers. An automated evaluation layer produces ongoing metrics on engagement and response quality to support refinement of the system.

Core claim

The platform establishes a generalizable robotics architecture that integrates caregiver-authored structured biographical knowledge, local edge intelligence, and embodied agents into a unified loop, enabling personalized emotion-aware dialogue and scalable deployment across heterogeneous robots with privacy preservation and low latency.

What carries the argument

The local edge interaction server that decouples multimodal perception, reasoning, and dialogue policy conditioning from specific robot hardware, supported by the cloud portal for ingesting and structuring caregiver biographical knowledge.

If this is right

Enables the same core interaction logic to run on different robotic platforms without hardware-specific redesign.
Supports accumulation of biographical data over sessions for longitudinal personalization of exercises.
Generates structured metrics at scale that can drive data-driven model updates and inform intervention planning.
Keeps sensitive processing local to preserve privacy while still allowing remote caregiver contributions.
Provides a template for similar stakeholder-in-the-loop systems in other care domains.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

The architecture could be tested for adaptation to other cognitive support needs such as post-stroke rehabilitation or mild cognitive impairment.
The collected interaction metrics might serve as a starting point for standardized benchmarks of robotic cognitive engagement tools.
Integration of the evaluation layer with electronic health records could allow clinicians to review engagement patterns directly.
Scaling to additional sites would reveal whether the edge-cloud split maintains performance as network variability increases.

Load-bearing premise

Caregiver-authored biographical knowledge can be reliably structured and used to condition dialogue policies across heterogeneous robots and sites without introducing inconsistencies or privacy issues.

What would settle it

A multi-site deployment in which caregiver-provided knowledge produces inconsistent or inappropriate dialogue responses or where measured end-to-end latency exceeds six seconds under normal operating conditions.

Figures

Figures reproduced from arXiv: 2604.16408 by Fengpei Yuan, Ruth Palan Lopez, Shu Fen Wung, Wenzheng Zhao.

**Figure 1.** Figure 1: System architecture of the Speaking Memories framework, illustrating a layered host–edge–cloud design for emotion-aware reminiscence interaction. The Hardware Layer interfaces with the user through onboard sensors and actuators. The Edge Robot Layer performs real-time multimodal sensing, lightweight context aggregation, and robot-side interaction state management, enabling low-latency perception and feedba… view at source ↗

**Figure 2.** Figure 2: Pipeline of the Speaking Memories platform, a distributed, stakeholder-in-the-loop architecture for adaptive reminiscence interaction. The system comprises three tightly coupled layers. (Left) A multimodal user input layer acquires visual, auditory, and textual cues from the participant during realtime interaction with an embodied robot agent. (Center) A local edge interaction server decouples multimodal … view at source ↗

**Figure 3.** Figure 3: System software flow diagram of the Speaking Memories framework for adaptive reminiscence interaction. Colored boxes represent different system components, white boxes with borders denote data flow and information exchange. Italicized text without boxes indicates user actions, while nonitalicized text without boxes represents Robot/User-executed actions. The detailed software flow of the Agent robot with… view at source ↗

**Figure 4.** Figure 4: Structured dataset format. Each session folder contains: (i) [PITH_FULL_IMAGE:figures/full_fig_p009_4.png] view at source ↗

**Figure 5.** Figure 5: Upon enrollment, individuals who met the inclusion [PITH_FULL_IMAGE:figures/full_fig_p010_5.png] view at source ↗

**Figure 6.** Figure 6: Real-world deployment of the Speaking Memories framework using two different hardware configurations at an elder care facility. (a) The left deployment used Robot I, relied soly on Pepper’s native hardware, using its onboard microphone, camera, and tablet for multimodal interaction. (b) The right deployment used Robot II, a Jetson-based edge client, where sensing and feedback were executed on an external J… view at source ↗

read the original abstract

We present Speaking Memories, a distributed, stakeholder-in-the-loop robotic interaction platform for personalized cognitive exercise support. Rather than a single robot-centric system, Speaking Memories is designed as a generalizable robotics architecture that integrates caregiver-authored knowledge, local edge intelligence, and embodied robotic agents into a unified socio-technical loop. The platform fuses auditory, visual, and textual signals to enable emotion-aware, personalized dialogue, while decoupling multimodal perception and reasoning from robot-specific hardware through a local edge interaction server. This design achieves low-latency, privacy-preserving operation and supports scalable deployment across heterogeneous robotic embodiments. Caregivers and family members contribute structured biographical knowledge via a secure cloud portal, which conditions downstream dialogue policies and enables longitudinal personalization across interaction sessions. Beyond real-time interaction, the system incorporates an automated multimodal evaluation layer that continuously analyzes user responses, affective cues, and engagement patterns, producing structured interaction metrics at scale. These metrics support systematic assessment of interaction quality, enable data-driven model fine-tuning, and lay the foundation for future clinician- and caregiver-informed personalization and intervention planning. We evaluate the platform through real-world deployments, measuring end-to-end latency, dialogue coherence, interaction stability, and stakeholder-reported usability and engagement. Results demonstrate sub-6-second response latency, robust multimodal synchronization, and consistently positive feedback from both participants and caregivers. Furthermore, subsets of the dataset can be shared upon request, subject to participant consent and IRB constraints.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Desk Editor's Note private letter to a colleague

The edge-cloud architecture for caregiver-driven robot exercises in dementia care is a practical design but the latency and feedback claims rest on unreported deployment details.

read the letter

The main point is that this paper lays out Speaking Memories as an edge-host-cloud platform that keeps robot hardware interchangeable while feeding caregiver biographical knowledge into personalized cognitive exercise dialogues for dementia patients. The automated multimodal evaluator that turns interaction data into structured metrics is another piece of the setup. What stands out is the clean separation of perception and reasoning on the local edge server, which supports low-latency operation and privacy without tying everything to one robot model. The cloud portal for caregivers to add structured personal history is a straightforward way to enable longitudinal personalization across sessions and sites. That combination addresses a real deployment need in multi-robot, multi-site care settings. The paper does a decent job spelling out how the pieces fit together for scalable, stakeholder-in-the-loop use. The soft spots sit in the results. The abstract reports sub-6-second end-to-end latency, robust synchronization, and consistently positive feedback from deployments, yet supplies no participant counts, site numbers, session totals, hardware specs, or measurement definitions for latency and synchronization. Without those, it is difficult to judge whether the robot-agnostic claim holds under varied network conditions or whether the caregiver input stays consistent. The stress-test note correctly flags this gap. This work is aimed at applied robotics researchers and clinicians focused on non-pharmacological dementia interventions. Readers looking for concrete system architecture ideas will find value in the integration choices even if the evaluation section needs expansion. The central design argument holds up as a practical proposal, so the paper deserves a serious referee to press for the missing deployment data and methods. I would send it to peer review.

Referee Report

2 major / 0 minor

Summary. The paper presents Speaking Memories, a distributed edge-host-cloud architecture for robot-agnostic, caregiver-in-the-loop personalized cognitive exercise in dementia care. Caregivers contribute structured biographical knowledge via a secure cloud portal that conditions dialogue policies; a local edge server handles multimodal (auditory/visual/textual) perception and emotion-aware reasoning while decoupling these from specific robot hardware. The system includes an automated evaluation layer for interaction metrics. Real-world multi-site deployments are reported to achieve sub-6-second end-to-end response latency, robust multimodal synchronization, and consistently positive feedback from participants and caregivers, with subsets of data available under consent constraints.

Significance. If the quantitative deployment results can be substantiated, the work would offer a practical, generalizable framework for scalable robotic cognitive support that preserves privacy through edge processing, incorporates longitudinal caregiver input, and generates structured metrics for ongoing assessment. This could meaningfully advance socio-technical systems in dementia care by demonstrating hardware-agnostic operation across heterogeneous robots and sites.

major comments (2)

[Evaluation / Abstract] Evaluation section / Abstract: The headline claims of sub-6-second response latency, robust multimodal synchronization, and consistently positive feedback are stated without any quantitative backing—participant counts, site counts, session volumes, hardware specifications for the edge server, precise latency measurement definition (utterance to robot output including network/cloud round-trips), synchronization tolerance metric, feedback instrument (survey items, scale, completion rate), or statistical tests. This absence prevents assessment of generalizability across robots and realistic network conditions.
[Abstract] Abstract: The decoupling claim (multimodal perception and reasoning separated from robot-specific hardware) is central to the architecture's generality, yet the manuscript provides no concrete evidence—such as cross-robot latency or synchronization comparisons—that this separation was successfully maintained or tested in the reported deployments.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We are grateful to the referee for the insightful comments that will help improve the clarity and rigor of our manuscript. We respond to each major comment below.

read point-by-point responses

Referee: [Evaluation / Abstract] Evaluation section / Abstract: The headline claims of sub-6-second response latency, robust multimodal synchronization, and consistently positive feedback are stated without any quantitative backing—participant counts, site counts, session volumes, hardware specifications for the edge server, precise latency measurement definition (utterance to robot output including network/cloud round-trips), synchronization tolerance metric, feedback instrument (survey items, scale, completion rate), or statistical tests. This absence prevents assessment of generalizability across robots and realistic network conditions.

Authors: We concur that the abstract and Evaluation section would benefit from more detailed quantitative information to support the headline claims. In the revised manuscript, we will augment the Evaluation section with the following: participant and site counts, session volumes, edge server hardware specifications, a clear definition of the end-to-end latency (including the measurement points from utterance to robot output and accounting for network and cloud round-trips), the synchronization tolerance metric, specifics of the feedback instrument (including survey items, scale, and completion rate), and results of any statistical tests. Additionally, we will discuss the implications for generalizability across robots and under realistic network conditions. revision: yes
Referee: [Abstract] Abstract: The decoupling claim (multimodal perception and reasoning separated from robot-specific hardware) is central to the architecture's generality, yet the manuscript provides no concrete evidence—such as cross-robot latency or synchronization comparisons—that this separation was successfully maintained or tested in the reported deployments.

Authors: The decoupling of multimodal perception and reasoning from robot-specific hardware is implemented via the local edge server using abstract interfaces. We agree that providing concrete evidence from the deployments would better substantiate this claim. In the revision, we will add cross-robot comparisons, including latency and synchronization metrics from the different robotic embodiments used in the multi-site deployments, to demonstrate that the separation was maintained and tested. revision: yes

Circularity Check

0 steps flagged

No significant circularity; results are deployment observations without self-referential derivations

full rationale

The paper presents a distributed robotics architecture and reports measured outcomes from real-world deployments (sub-6s latency, multimodal synchronization, positive feedback). No equations, fitted parameters, predictions, or uniqueness theorems are described that reduce claims to inputs by construction. Claims rest on observational data rather than self-citations or definitional loops, making the derivation chain self-contained against external benchmarks.

Axiom & Free-Parameter Ledger

0 free parameters · 2 axioms · 0 invented entities

The platform rests on standard assumptions in robotics and HCI that multimodal fusion enables emotion-aware dialogue and that caregiver knowledge improves personalization; no free parameters or invented entities are introduced in the abstract.

axioms (2)

domain assumption Multimodal auditory, visual, and textual signals can be fused to produce coherent, emotion-aware dialogue responses
Invoked in the description of the local edge interaction server
domain assumption Structured biographical knowledge from caregivers can condition dialogue policies for longitudinal personalization
Central to the cloud portal and personalization mechanism

pith-pipeline@v0.9.0 · 5575 in / 1299 out tokens · 40586 ms · 2026-05-13T22:57:24.896794+00:00 · methodology

discussion (0)

Reference graph

Works this paper leans on

41 extracted references · 41 canonical work pages · 1 internal anchor

[1]

Dementia,

World Health Organization, “Dementia,” https://www.who.int/news- room/fact-sheets/detail/dementia, 2025

work page 2025
[2]

Socially assistive robots in elderly care: a systematic review into effects and effectiveness,

R. Bemelmans, G. J. Gelderblom, P. Jonker, and L. De Witte, “Socially assistive robots in elderly care: a systematic review into effects and effectiveness,” Journal of the American Medical Directors Association , vol. 13, no. 2, pp. 114–120, 2012

work page 2012
[3]

Dementia prevention, intervention, and care: 2020 report of the lancet commission,

G. Livingston, J. Huntley, A. Sommerlad, D. Ames, C. Ballard, S. Baner- jee, C. Brayne, A. Burns, J. Cohen-Mansfield, C. Cooper et al. , “Dementia prevention, intervention, and care: 2020 report of the lancet commission,” The lancet, vol. 396, no. 10248, pp. 413–446, 2020

work page 2020
[4]

A frame- work for music-evoked autobiographical memories in robot-assisted tasks for people with dementia

P. R. de la Bletiere, M. Neerincx, R. Schaefer, and C. Oertel, “A frame- work for music-evoked autobiographical memories in robot-assisted tasks for people with dementia.”

work page
[5]

Socially assistive robotics,

M. J. Matari ´c and B. Scassellati, “Socially assistive robotics,” Springer handbook of robotics , pp. 1973–1994, 2016

work page 1973
[6]

Personalized socially assistive robots with end-to-end speech- language models for well-being support,

M. Fu, Z. Shi, M. Huang, S. Liu, M. Kian, Y . Song, and M. J. Matari´c, “Personalized socially assistive robots with end-to-end speech- language models for well-being support,” 2025. [Online]. Available: https://arxiv.org/abs/2507.14412

work page arXiv 2025
[7]

A systematic review and meta-analysis on the effect of reminiscence therapy for people with dementia,

K. Park, S. Lee, J. Yang, T. Song, and G.-R. S. Hong, “A systematic review and meta-analysis on the effect of reminiscence therapy for people with dementia,” International psychogeriatrics, vol. 31, no. 11, pp. 1581–1597, 2019

work page 2019
[8]

Positive emotional responses to socially assistive robots in people with dementia: pilot study,

E. Otaka, A. Osawa, K. Kato, Y . Obayashi, S. Uehara, M. Kamiya, K. Mizuno, S. Hashide, I. Kondo et al. , “Positive emotional responses to socially assistive robots in people with dementia: pilot study,” JMIR aging, vol. 7, no. 1, p. e52443, 2024

work page 2024
[9]

Cognitive exercise for persons with alzheimer’s disease and related dementia using a social robot,

M. Boltz, D. Bilal, Y .-L. Jao, M. Crane, J. Duzan, A. Bahour, and X. Zhao, “Cognitive exercise for persons with alzheimer’s disease and related dementia using a social robot,” IEEE Transactions on Robotics , vol. 39, no. 4, pp. 3332–3346, 2023

work page 2023
[10]

Toward personalized affect-aware socially assistive robot tutors for long-term interventions with children with autism,

Z. Shi, T. R. Groechel, S. Jain, K. Chima, O. Rudovic, and M. J. Matari ´c, “Toward personalized affect-aware socially assistive robot tutors for long-term interventions with children with autism,” ACM Transactions on Human-Robot Interaction (THRI) , vol. 11, no. 4, pp. 1–28, 2022

work page 2022
[11]

The benefits of and barriers to using a social robot paro in care settings: a scoping review,

L. Hung, C. Liu, E. Woldum, A. Au-Yeung, A. Berndt, C. Wallsworth, N. Horne, M. Gregorio, J. Mann, and H. Chaudhury, “The benefits of and barriers to using a social robot paro in care settings: a scoping review,”BMC geriatrics, vol. 19, no. 1, p. 232, 2019

work page 2019
[12]

Robots for elderly care: review, multi-criteria optimization model and qualitative case study,

B. Sawik, S. Tobis, E. Baum, A. Suwalska, S. Kropi ´nska, K. Stachnik, E. P´erez-Bernabeu, M. Cildoz, A. Agustin, and K. Wieczorowska-Tobis, “Robots for elderly care: review, multi-criteria optimization model and qualitative case study,” in Healthcare, vol. 11, no. 9. MDPI, 2023, p. 1286

work page 2023
[13]

Lami: Large language models for multi-modal human-robot interaction,

C. Wang, S. Hasler, D. Tanneberg, F. Ocker, F. Joublin, A. Ceravola, J. Deigmoeller, and M. Gienger, “Lami: Large language models for multi-modal human-robot interaction,” in Extended Abstracts of the CHI Conference on Human Factors in Computing Systems , 2024, pp. 1–10

work page 2024
[14]

Dobby: a conversational service robot driven by gpt-4,

C. Stark, B. Chun, C. Charleston, V . Ravi, L. Pabon, S. Sunkari, T. Mohan, P. Stone, and J. Hart, “Dobby: a conversational service robot driven by gpt-4,” in 2024 33rd IEEE International Conference on Robot and Human Interactive Communication (ROMAN) . IEEE, 2024, pp. 1362–1369

work page 2024
[15]

Defining socially assistive robotics,

D. Feil-Seifer and M. J. Mataric, “Defining socially assistive robotics,” in 9th International Conference on Rehabilitation Robotics, 2005. ICORR

work page 2005
[16]

IEEE, 2005, pp. 465–468

work page 2005
[17]

Kaspar–a minimally expressive humanoid robot for human–robot interaction research,

K. Dautenhahn, C. L. Nehaniv, M. L. Walters, B. Robins, H. Kose- Bagci, N. A. Mirza, and M. Blow, “Kaspar–a minimally expressive humanoid robot for human–robot interaction research,” Applied Bionics and Biomechanics, vol. 6, no. 3-4, pp. 369–397, 2009

work page 2009
[18]

Use of a humanoid robot in supporting dementia care: a qualitative analysis,

Y .-J. Liao, Y .-L. Jao, M. Boltz, O. T. Adekeye, D. Berish, and X. Zhao, “Use of a humanoid robot in supporting dementia care: a qualitative analysis,” SAGE open nursing , vol. 9, p. 23779608231179528, 2023

work page 2023
[19]

A systematic review of robotic rehabilitation for cognitive training,

E. Klavon, Z. Liu, and X. Zhao, “A systematic review of robotic rehabilitation for cognitive training,”Frontiers in Robotics and AI, vol. 8, p. 605715, 2021

work page 2021
[20]

Edge robotics: Edge-computing-accelerated multirobot simultaneous localization and mapping,

P. Huang, L. Zeng, X. Chen, K. Luo, Z. Zhou, and S. Yu, “Edge robotics: Edge-computing-accelerated multirobot simultaneous localization and mapping,” IEEE Internet of Things Journal , vol. 9, no. 15, pp. 14 087– 14 102, 2022

work page 2022
[21]

Cloud robotics: architecture, challenges and applications,

G. Hu, W. P. Tay, and Y . Wen, “Cloud robotics: architecture, challenges and applications,” IEEE network, vol. 26, no. 3, pp. 21–28, 2012

work page 2012
[22]

Distributed robotic systems in the edge-cloud continuum with ros 2: A review on novel architectures and technology readiness,

J. Zhang, F. Keramat, X. Yu, D. M. Hern ´andez, J. P. Queralta, and T. Westerlund, “Distributed robotic systems in the edge-cloud continuum with ros 2: A review on novel architectures and technology readiness,” in 2022 Seventh International Conference on Fog and Mobile Edge Computing (FMEC). IEEE, 2022, pp. 1–8

work page 2022
[23]

Privacy- preserving federated learning for human intention modeling in pediatric cerebral palsy using extended reality,

S. Anari, R. Ranjbarzadeh, M. Cunneen, and M. Bendechache, “Privacy- preserving federated learning for human intention modeling in pediatric cerebral palsy using extended reality,” in 2025 IEEE 49th Annual Computers, Software, and Applications Conference (COMPSAC). IEEE, 2025, pp. 1–6

work page 2025
[24]

Cloud-edge-device collaboration mechanisms of deep learning models for smart robots in mass personalization,

C. Yang, Y . Wang, S. Lan, L. Wang, W. Shen, and G. Q. Huang, “Cloud-edge-device collaboration mechanisms of deep learning models for smart robots in mass personalization,” Robotics and Computer- Integrated Manufacturing, vol. 77, p. 102351, 2022

work page 2022
[25]

Cognitive intervention through photo-integrated conversation moderated by robots (picmor) program: a randomized controlled trial,

M. Otake-Matsuura, S. Tokunaga, K. Watanabe, M. S. Abe, T. Sekiguchi, H. Sugimoto, T. Kishimoto, and T. Kudo, “Cognitive intervention through photo-integrated conversation moderated by robots (picmor) program: a randomized controlled trial,” Frontiers in Robotics and AI , vol. 8, p. 633076, 2021

work page 2021
[26]

Learning-based strategy design for robot-assisted reminiscence therapy based on a developed model for people with dementia,

R. Zhang, D. Bilal, and X. Zhao, “Learning-based strategy design for robot-assisted reminiscence therapy based on a developed model for people with dementia,” in International Conference on Social Robotics . Springer, 2021, pp. 432–442

work page 2021
[27]

Socially assistive robots for people living with dementia in long- term facilities: a systematic review and meta-analysis of randomized controlled trials,

C.-J. Hsieh, P.-S. Li, C.-H. Wang, S.-L. Lin, T.-C. Hsu, and C.-M. T. Tsai, “Socially assistive robots for people living with dementia in long- term facilities: a systematic review and meta-analysis of randomized controlled trials,” Gerontology, vol. 69, no. 8, pp. 1027–1042, 2023

work page 2023
[28]

Gpt-4v(ision) system card,

OpenAI, “Gpt-4v(ision) system card,” 2023. [Online]. Available: https://api.semanticscholar.org/CorpusID:263218031

work page 2023
[29]

Palm-e: An embodied multimodal language model,

D. Driess, F. Xia, M. S. Sajjadi, C. Lynch, A. Chowdhery, A. Wahid, J. Tompson, Q. Vuong, T. Yu, W. Huang et al., “Palm-e: An embodied multimodal language model,” 2023

work page 2023
[30]

Rt-2: Vision-language-action models transfer web knowledge to robotic control,

B. Zitkovich, T. Yu, S. Xu, P. Xu, T. Xiao, F. Xia, J. Wu, P. Wohlhart, S. Welker, A. Wahid et al. , “Rt-2: Vision-language-action models transfer web knowledge to robotic control,” in Conference on Robot Learning. PMLR, 2023, pp. 2165–2183

work page 2023
[31]

Inner Monologue: Embodied Reasoning through Planning with Language Models

W. Huang, F. Xia, T. Xiao, H. Chan, J. Liang, P. Florence, A. Zeng, J. Tompson, I. Mordatch, Y . Chebotaret al., “Inner monologue: Embod- ied reasoning through planning with language models,” arXiv preprint arXiv:2207.05608, 2022

work page internal anchor Pith review Pith/arXiv arXiv 2022
[32]

Assistant robot enhances the perceived communication quality of people with dementia: A proof of concept,

D. Zhou, E. I. Barakova, P. An, and M. Rauterberg, “Assistant robot enhances the perceived communication quality of people with dementia: A proof of concept,” IEEE Transactions on Human-Machine Systems , vol. 52, no. 3, pp. 332–342, 2021

work page 2021
[33]

Effectiveness of companion robot care for dementia: a systematic review and meta-analysis,

L.-C. Lu, S.-H. Lan, Y .-P. Hsieh, L.-Y . Lin, S.-J. Lan, and J.-C. Chen, “Effectiveness of companion robot care for dementia: a systematic review and meta-analysis,”Innovation in aging, vol. 5, no. 2, p. igab013, 2021

work page 2021
[34]

Dialogue systems and conversational agents for patients with dementia: The human–robot interaction,

A. Russo, G. D’Onofrio, A. Gangemi, F. Giuliani, M. Mongiovi, F. Ricciardi, F. Greco, F. Cavallo, P. Dario, D. Sancarloet al., “Dialogue systems and conversational agents for patients with dementia: The human–robot interaction,” Rejuvenation research , vol. 22, no. 2, pp. 109–120, 2019

work page 2019
[35]

Nyamathi, N

A. Nyamathi, N. Dutt, J.-A. Lee, A. M. Rahmani, M. Rasouli, D. Krogh, E. Krogh, D. Sultzer, H. Rashid, H. Liaqat et al. , “Establishing the foundations of emotional intelligence in care companion robots to mitigate agitation among high-risk patients with dementia: protocol for an empathetic patient-robot interaction study,”JMIR Research Protocols, vol. 13...

work page 2024
[36]

Advanced-comfort: Usability testing of a care planning intervention for nursing home residents with advanced dementia,

R. P. Lopez, A. Wei, J. R. Locke, and E. Plys, “Advanced-comfort: Usability testing of a care planning intervention for nursing home residents with advanced dementia,” Journal of Gerontological Nursing , vol. 49, no. 11, pp. 15–23, 2023

work page 2023
[37]

Robust speech recognition via large-scale weak supervi- sion,

A. Radford, J. W. Kim, T. Xu, G. Brockman, C. McLeavey, and I. Sutskever, “Robust speech recognition via large-scale weak supervi- sion,” in International conference on machine learning . PMLR, 2023, pp. 28 492–28 518. 21

work page 2023
[38]

Design and validation of a frame- work for the creation of user experience questionnaires,

M. Schrepp and J. Thomaschewski, “Design and validation of a frame- work for the creation of user experience questionnaires,” IJIMAI, vol. 5, no. 7, pp. 88–95, 2019

work page 2019
[39]

Comprehension of acoustically degraded emotional prosody in alzheimer’s disease and primary progressive apha- sia,

J. Jiang, J. C. Johnson, M.-C. Requena-Komuro, E. Benhamou, H. Sivasathiaseelan, A. Chokesuwattanaskul, A. Nelson, R. Nortley, R. S. Weil, A. V olkmeret al., “Comprehension of acoustically degraded emotional prosody in alzheimer’s disease and primary progressive apha- sia,” Scientific Reports, vol. 14, no. 1, p. 31332, 2024

work page 2024
[40]

Investigating acoustic and psycholinguistic predictors of cognitive impairment in older adults: modeling study,

V . D. Badal, J. M. Reinen, E. W. Twamley, E. E. Lee, R. P. Fellows, E. Bilal, and C. A. Depp, “Investigating acoustic and psycholinguistic predictors of cognitive impairment in older adults: modeling study,” JMIR aging, vol. 7, no. 1, p. e54655, 2024

work page 2024
[41]

Artificial emotional intelligence in socially assistive robots for older adults: a pilot study,

H. Abdollahi, M. H. Mahoor, R. Zandie, J. Siewierski, and S. H. Qualls, “Artificial emotional intelligence in socially assistive robots for older adults: a pilot study,” IEEE Transactions on Affective Computing , vol. 14, no. 3, pp. 2020–2032, 2022

work page 2020