本文選題：相空間重構(gòu) + 非線性幾何特征�。� 參考：《西安電子科技大學(xué)學(xué)報(bào)》2017年06期

【摘要】：針對現(xiàn)有語音情感特征在表征情感信息上的不完整,將相空間重構(gòu)理論引入到情感語音的特征提取中.通過分析不同語音情感狀態(tài)下相空間重構(gòu)的幾何特性,提取了該重構(gòu)相空間下基于軌跡的描述輪廓的5種非線性幾何特征作為新的情感語音特征參數(shù),并根據(jù)情感與特征映射的關(guān)系提出一種特征參數(shù)優(yōu)化方法.首先,選用德語柏林語音庫中的高興、悲傷、中性和生氣4種情感作為實(shí)驗(yàn)樣本;其次,提取非線性幾何特征和非線性屬性特征(最小延遲時(shí)間、關(guān)聯(lián)維數(shù)、Kolmogorov熵、最大Lyapunov指數(shù)和Hurst指數(shù));最后,根據(jù)設(shè)計(jì)方案采用支持向量機(jī)進(jìn)行情感語音識(shí)別.實(shí)驗(yàn)結(jié)果表明,該特征相較于非線性屬性特征在情感語音識(shí)別上有較強(qiáng)的優(yōu)勢度,聯(lián)合非線性屬性特征后,通過特征參數(shù)優(yōu)化的方法獲得了最優(yōu)的非線性特征集合,驗(yàn)證了該方法的實(shí)用性.
[Abstract]:Aiming at the incomplete representation of emotional information in existing speech emotional features, the theory of phase space reconstruction is introduced into the feature extraction of emotional speech. By analyzing the geometric characteristics of phase space reconstruction in different speech emotion states, five kinds of nonlinear geometric features based on trajectory describing contour in the reconstructed phase space are extracted as new emotional speech feature parameters. According to the relationship between emotion and feature mapping, a feature parameter optimization method is proposed. Firstly, the happy, sad, neutral and angry emotions in the German Berlin language corpus are selected as experimental samples; secondly, the nonlinear geometric features and nonlinear attribute features (minimum delay time, correlation dimension and Kolmogorov entropy) are extracted. The maximum Lyapunov exponent and Hurst exponent are obtained. Finally, support vector machine is used for emotional speech recognition according to the design scheme. The experimental results show that the feature has a strong superiority in emotional speech recognition compared with the nonlinear attribute feature. After combining the nonlinear attribute feature, the optimal nonlinear feature set is obtained by the method of feature parameter optimization. The practicability of the method is verified.
【作者單位】： 太原理工大學(xué)信息工程學(xué)院;
【基金】：國家自然科學(xué)基金資助項(xiàng)目(61371193)
【分類號】：TN912.3
，

本文編號：1784869