人机语音交互中的情感语音处理  

Emotional Speech Processing in Human-Computer Speech Interface

作　　者：姜晓庆[1] 崔世耀[1] 殷艳华[2] 

机构地区：[1]济南大学信息科学与工程学院,山东济南250022 [2]山东省科学院自动化研究所,山东济南250014

出　　处：《济南大学学报（自然科学版）》2008年第4期354-357,共4页Journal of University of Jinan(Science and Technology)

摘　　要：选取三种典型的情感状态,通过对在不同情感状态下大量取样的语音样本的基频、能量、时长及相关韵律特征参数作统计分析,基于统计结果使用PCA方法进行情感状态识别实验,识别准确率达91.67%。结合情感识别结果,使用DTW算法通过模式匹配进行小词汇表的语音识别,提高语音识别正确率;给出输出语音韵律特征参数的调整方法,使人机语音交互得到更加人性化的改进。Emotional speech processing technology plays an important role in the improvement of HCI. In this paper, numerous speech samples of same speaker are recorded under three primary＂ emotions. Statistical analysis is used to analyze the pitch, energy, time and the related prosodic parameters, based on which PCA methods is used to recognize emotion states and the correct rate is 91. 67%. Combined with the emotion recognition results, results of speech reeognition using DTW and pattern matching arithmetic are improved. Meanwhile, methods for modifying speech prosodic characteristics are researched to make HCI more intelligent.

关 键 词：情感语音 人机交互 情感识别 语音识别 

分 类 号：TN912.34[电子电信—通信与信息系统]