A Modular Multimodal Dialog Architecture for Digital PROM Collection

Hillmann, S., Harnisch, P., Schuhmann, D., Ashrafi, N. & Voigt-Antons, J.-N.
Paper presented at the Conference on Electronic Speech Signal Processing 2026 (ESSV 2026), Eichstätt, Germany, March 2026
Summary
This paper presents a modular multimodal dialog architecture designed to support the digital collection of Patient-Reported Outcome Measures (PROMs). The architecture integrates speech, touch, and visual interaction components and emphasizes extensibility, robustness, and adaptability to different user groups and clinical contexts. The work discusses design requirements, system components, and interaction flow, aiming to facilitate reliable and user-centered PROM acquisition in healthcare applications.
Written for this site, the published abstract is with the publisher.
Cite as
Hillmann, S., Harnisch, P., Schuhmann, D., Ashrafi, N. & Voigt-Antons, J.-N. (2026, March). A Modular Multimodal Dialog Architecture for Digital PROM Collection. Paper presented at the Conference on Electronic Speech Signal Processing 2026 (ESSV 2026). Eichstätt, Germany.