采用GW-MFCC模型空间参数的语音情感识别-计算机工程与应用.PDFVIP

Computer Engineering and Applications 计算机工程与应用 2015 ，51（10） 219 采用GW-MFCC 模型空间参数的语音情感识别 沈 燕，肖仲喆，李冰洁，周孝进，周 强，陶 智 SHEN Yan, XIAO Zhongzhe, LI Bingjie, ZHOU Xiaojin, ZHOU Qiang, TAO Zhi 苏州大学 物理科学与技术学院，江苏 苏州 215006 School of Physical Science and Technology, Soochow University, Suzhou, Jiangsu 215006, China SHEN Yan, XIAO Zhongzhe, LI Bingjie, et al. Speech emotion recognition using GW-MFCC feature. Computer Engineering and Applications, 2015, 51 （10）：219-222. Abstract ：Aiming the insufficient expression of speech emotion with single type of speech features, a new feature weight- ed MFCC （WMFCC ）is proposed combining LSF with good interpolation and quantization performance and MFCC which presents human hearing characters. GMM model is applied to this feature to obtain high level model space parameter GW-MFCC in order to further improve the emotion recognition rate with detailed information. Experiments are carried out on EMO-DB. The correct recognition rates are 5.7% and 6.9% higher than using MFCC and LSF respectively. The experiment results show that the GW-MFCC feature can effectively convey emotional information in speech, thus can improve the performance in the emotion recognition. Key words ：speech emotion recognition; Linear Spectrum Frequence （LSF ）; Mel-Frequency Cepstral Coeffients（MFCC ）; Gaussian Mixture Model（GMM ）; model space 摘 要：针对单一语音特征对语音情感表达不完整的问题，将具有良好量化和插值特性的LSF 参数与体现人耳听觉 特性的MFCC 参数相融合，提出基于线谱权重的MFCC （WMFCC ）新特征。同时，通过高斯混合模型来对该参数建 立模型空间，进一步得到GW-MFCC 模型空间参数，以获取更高维的细节信息，进一步提高情感识别性能。采用柏 林情感语料库进行验证，新参数的识别率比传统的MFCC 和LSF 分别有5.7%和6.9% 的提高。实验结果表明，提出 的WMFCC 以及GW-MFCC 参数可以有效地表现语音情感信息，提高语音情感识别率。 关键词：语音情感识别；线谱对频率（LSF ）；Mel 频率倒谱系数（MFCC ）；高斯混合模型；模型空间 文献标志码：A 中图分类号：TP391 doi ：10.3778/j.issn. 1002-8331.1309-0381 [6-7] 1 引言