VedicTHG: 用于教育拟人化角色中低资源语音生成的符号吠陀计算
VedicTHG: Symbolic Vedic Computation for Low-Resource Talking-Head Generation in Educational Avatars
AI总结：
VedicTHG通过符号吠陀计算在CPU上实现低资源谈话头生成，减少计算负载和延迟，提升教育拟人化角色的实用性
摘要：
谈话头拟人化角色在教育技术中日益被采用，以通过社会存在性和提高参与度来传递内容。然而，许多最近的谈话头生成（THG）方法依赖于以GPU为中心的神经渲染、大规模训练集或高容量扩散模型，这限制了在离线或资源受限的学习环境中部署。本文描述了一种确定性和以CPU为中心的THG框架，称为符号吠陀计算，该框架将语音转换为时间对齐的音素流，将音素映射到紧凑的viseme库存，并通过受吠陀咒语Urdhva Tiryakbhyam启发的符号协articulation生成平滑的viseme轨迹。一个轻量级的2D渲染器执行感兴趣区域（ROI）变形和嘴巴合成，以稳定的方式支持在商用CPU上实时合成。实验报告了在仅CPU执行时的同步准确性、时间稳定性和身份一致性，并与代表性的CPU可行基线进行基准测试。结果表明，可以在显著减少计算负载和延迟的同时实现可接受的嘴唇同步质量，支持在低端硬件上的实用教育拟人化角色。GitHub: https://vineetkumarrakesh.github.io/vedicthg
英文摘要：
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
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
