Date of Graduation

7-2026

Document Type

Thesis

Degree Name

Master of Science in Computer Science (MS)

Degree Level

Graduate

Department

Electrical Engineering and Computer Science

Advisor/Mentor

Martin Gomez, Alejandro

Committee Member

Nelson, Alexander

Second Committee Member

Lee, Joomi

Third Committee Member

Dang, Tuan

Keywords

Audio-Driven, Photorealistic Avatars, Teleconsultation, development, evaluation framework, constrained bandwidth environments

Abstract

Telehealth can improve access to healthcare services, especially for patients in rural and underserved areas. Many telehealth services use video communication to provide real-time interaction and a visible connection between patients and healthcare providers. However, video communication requires continuous transmission of audio and video data. When network conditions are limited or unreliable, audio and video interruptions can reduce communication quality. This thesis explores an audio-driven photorealistic avatar as a possible visual communication layer for teleconsultation without requiring continuous webcam video transmission. It develops two connected frameworks: the Audio-Driven Photorealistic Avatar Communication Framework and the Evaluation Framework. The Audio-Driven Photorealistic Avatar Communication Framework creates a subject-specific photorealistic avatar that preserves the visual appearance of a healthcare provider and animates it from speech. It contains an Avatar Generation Module and an Audio-Driven Avatar Animation Module. The Avatar Generation Module uses a one-time subject recording to create the avatar, while the Avatar Animation Module uses prerecorded or microphone-captured speech to generate its facial motion. The Evaluation Framework supports the creation of reproducible audio and avatar degradations for future assessment of communication quality and user acceptability under simulated bandwidth-related conditions. It contains a Bandwidth Degradation Module and a User Experience Assessment Module. The Degradation Module creates evaluation clips containing simulated effects associated with constrained or unreliable communication, such as audio/visual drops, reduced avatar update rates, and timing jitter. The Assessment Module presents the prepared clips and records time-aligned communication-acceptability responses. The completed work in the thesis provides a foundation for a future evaluation to assess communication quality and user acceptability of an avatar-based communication system under simulated bandwidth-related degradations. The thesis does not conduct a participant study or validate the framework over a physical network.

Download

Share

COinS