一体机式虚拟数字人的设计与实现
Design and Implementation of All-in-One-Box Virtual Digital Human
黄林 1林健 1徐驰 1罗明宇 1王武双 1鲁晓丹1
作者信息
- 1. 东云睿连(武汉)计算技术有限公司,湖北 武汉 430200
- 折叠
摘要
虚拟数字人是人工智能与元宇宙应用的交叉点,也是当今线上与线下人机交互的新兴渠道之一.虚拟数字人涉及控制引擎、自然语言处理、3D图形渲染、语音识别与合成等技术领域,需要软硬件栈多层次的协同设计.为此,基于一体机部署模式的OMHuman虚拟数字人解决方案提出一套松耦合式控制引擎,采用独立显卡实现图形渲染,并通过自研算法在Intel OpenVINO计算引擎上实现人工智能模型推理,解决了传统方案在语音—动作协同控制等诸多方面的不足,同时兼顾了最终用户体验、开发成本与部署成本.比较测试表明,OMHuman虚拟数字人模型推理性能为传统引擎的2～3倍,图形渲染效率为核芯显卡的2倍,能够以自然的方式满足人机交互需求,目前已在虚拟主持人、智能数据分析师等场景得到成功应用.
Abstract
Virtual digital humans are the intersection of artificial intelligence and metaverse applications,involving technology fields such as control engines,natural language processing,3D graphics rendering,speech recognition and synthesis,and require multi-level collaborative design of software and hardware stacks.To this end,a loosely coupled control engine is proposed for the OMHuman virtual digital human solu-tion based on the all-in-one machine deployment mode.It uses an independent graphics card to achieve graphics rendering and implements ar-tificial intelligence model inference on the Intel OpenVINO computing engine through self-developed algorithms.This solves the shortcomings of traditional solutions in voice action collaborative control and other aspects,while also taking into account the end user experience,develop-ment costs,and deployment costs.Comparative tests have shown that the reasoning performance of the OMHuman virtual digital human model is 2-3 times that of traditional engines,and the graphics rendering efficiency is twice that of core graphics cards.It can meet human-computer interaction needs in a natural way and has been successfully applied in scenarios such as virtual hosts and intelligent data analysts.
关键词
虚拟数字人/人工智能/一体机/控制引擎/自然语言处理/图形渲染Key words
virtual digital human/artificial intelligence/all-in-one-box/control engine/natural language processing/graphics rendering引用本文复制引用
基金项目
武汉东湖高新区第十三批3551光谷人才计划(M165)
Intel Marketing Exchange项目(581394)
出版年
2024
国家科技期刊平台
NSTL
万方数据