基于IOHMM的语音驱动唇动合成系统  

Speech-driven Lip Movement Synthesize System Based on IOHMM

作　　者：马娥娥[1] 刘颖[1] 王成儒[1] 

机构地区：[1]燕山大学信息科学与工程学院,秦皇岛066004

出　　处：《计算机工程》2009年第18期283-284,F0003,共3页Computer Engineering

摘　　要：针对语音驱动的唇动合成系统进行基于小波包分析的语音特征提取,采用特征差分和口形帧前后关联的多帧语音表征语音的动态特性,利用主成分分析降低输入语音的特征维数。采用基于输入输出隐马尔可夫模型(IOHMM)的音视频映射模型构建语音驱动唇动合成系统,实验表明提取的语音参数比传统Mel倒谱系数鲁棒性更好,合成的口形序列更连贯、自然。This paper processes speech feature extraction based on wavelet packet analysis aiming at speech-driven lip movement synthesize. It uses feature difference and multi-frames speech based on association relationship of lip frames to express dynamic characteristic for speech, utilizes Principal Component Analysis（PCA） to reduce dimensions of the input speech. It introduces speech-visual mapping models based on Input-Output Hidden Markov ModeI（IOHMM） to obtain speech-driven lip movement synthesize system. Experiment indicates that speech features are more robust than traditional Mel-frequency cepstrum coefficient, can synthesize coherent and natural lip sequences.

关 键 词：可视语音 小波包分析 主成分分析 

分 类 号：TP391.42[自动化与计算机技术—计算机应用技术]