摘要
提出一种基于协方差描述子和黎曼流形的语音情感识别方法.根据提取的语音声学特征,计算协方差矩阵用于表征语句的情感信息.考虑到非奇异协方差矩阵所构成空间的高维特性,引入一种仿射不变度量使得该空间满足黎曼流形的要求.进而根据微分几何,建立基于黎曼流形的算法架构.实验证明,该方法在语音情感识别中获得较好的识别效果,尤其在噪声环境下能更有效地提高识别准确率.
An algorithm for speech emotion recognition is proposed based on covariance descriptor and Riemannian manifold. According to the extracted acoustic features, covariance matrices are computed as the emotion descriptors of sentences. With the consideration of high dimensional characteristic of the space constructed by non-singular covariance matrices, an affine invariance metric is adopted to make the space meet the requirement of Riemannian manifold. With differential geometry, the speech emotion recognition is performed on the manifold. The experimental results show a significant improvement in recognition accuracy, especially under noisy environments.
出处
《模式识别与人工智能》
EI
CSCD
北大核心
2009年第5期673-677,共5页
Pattern Recognition and Artificial Intelligence
基金
国家自然科学基金项目(No.60873124)
国家科技支撑计划项目(No.2008BAH26B02)资助
关键词
语音情感识别
协方差描述子
黎曼流形
噪声环境
支持向量机(SVM)
Speech Emotion Recognition, Covariance Descriptor, Riemannian Manifold, Noisy Environment, Support Vector Machine （SVM）
