摘要
针对音、视频双模态语音识别能有效地提高噪声环境下的识别率的特性,本文设计了车载语音控制指令识别实验系统。该系统模拟车载环境,把说话时的视频信息融入到语音识别系统中,系统分为模型训练、离线识别和在线识别3部分。在线识别全程采用语音作为人机交互手段,并具备用户自适应的功能。离线识别部分将系统产生的数据分层次进行统计,非常适合进行双模态语音识别算法研究。
In order to improve the recognition correct rate for audio-visual bimodal speech recognition in noise environment,this paper designs and implements a speech recognition system.This system simulates car environment and puts the speaking video information into speech recognition system.This system consists of three parts,model training,off-line recognition and on-line recognition.On-line recognition using voice as human-computer interaction,has the function of adaptive user.Off-line recognition has an analysis of data at different levels for system to produced,it is very suitable for bimodal speech recognition.
出处
《计算机与现代化》
2010年第8期211-215,共5页
Computer and Modernization
基金
国家自然科学基金资助项目(60572141
60602014)
关键词
双模态语音识别
语音识别
车载控制
bimodal speech recognition
speech recognition
vehicular control
