VedicTHG: Symbolic Vedic Computation for Low-Resource Talking-Head Generation in Educational Avatars

TL;DR

This paper introduces VedicTHG, a symbolic, CPU-based talking-head generation framework that enables real-time, resource-efficient educational avatars with good lip-sync accuracy on low-end hardware.

Contribution

It presents a novel symbolic Vedic computation approach for low-resource talking-head generation, reducing reliance on neural networks and high-capacity models.

Findings

Achieves acceptable lip-sync quality on CPU-only systems.

Reduces computational load and latency significantly.

Supports real-time avatar synthesis on low-end hardware.

Abstract

Talking-head avatars are increasingly adopted in educational technology to deliver content with social presence and improved engagement. However, many recent talking-head generation (THG) methods rely on GPU-centric neural rendering, large training sets, or high-capacity diffusion models, which limits deployment in offline or resource-constrained learning environments. A deterministic and CPU-oriented THG framework is described, termed Symbolic Vedic Computation, that converts speech to a time-aligned phoneme stream, maps phonemes to a compact viseme inventory, and produces smooth viseme trajectories through symbolic coarticulation inspired by Vedic sutra Urdhva Tiryakbhyam. A lightweight 2D renderer performs region-of-interest (ROI) warping and mouth compositing with stabilization to support real-time synthesis on commodity CPUs. Experiments report synchronization accuracy, temporal stability, and identity consistency under CPU-only execution, alongside benchmarking against representative CPU-feasible baselines. Results indicate that acceptable lip-sync quality can be achieved while substantially reducing computational load and latency, supporting practical educational avatars on low-end hardware. GitHub: https://vineetkumarrakesh.github.io/vedicthg