基于语谱图行投影的特定人二字汉语词汇识别  

Recognition to specific two words Chinese vocabulary based on projection matrix of spectrogram

作　　者：梁士利[1] 魏莹[1] 潘迪[1] 张玲[2] 许廷发[3] 王双维[1] LIANG Shi-li WEI Ying PAN Di ZHANG Ling XU Ting-fa WANG Shuang-wei(College of Physics, Northeast Normal University, Changchun 130024, China College of Science, Changchun University of Science and Technology, Changchun 130022, China Key Laboratory of Photoelectronic Imaging Technology and System of Ministry of Education, Beijing Institute of Technology, Beijing 100081,China)

机构地区：[1]东北师范大学物理学院,长春130024 [2]长春理工大学理学院,长春130022 [3]北京理工大学光电成像技术与系统教育部重点实验室,北京100081

出　　处：《吉林大学学报（工学版）》2017年第1期294-300,共7页Journal of Jilin University:Engineering and Technology Edition

基　　金：国家自然科学基金项目(61471111)

摘　　要：将图像处理技术应用到语音识别领域,在图像特征提取过程中,首先对语谱图进行等宽度分带行投影和二进宽度分带行投影,分别作为窄带语谱图的第1个特征集合和第2个特征集合,同时将语谱图进行再次图像傅里叶变换之后进行等宽度行投影,作为第3个特征集合。将上述3个特征集构造为特定人二字汉语词汇识别的特征向量,以支持向量机为分类器进行特定人二字汉语词汇整体识别。采用1000个语音样本进行仿真实验,结果表明,该方法对特定人二字汉语词汇的识别率可达92.8%,为汉语词汇的识别提供了新的思路。In the process of image feature extraction,the image processing technique is applied to the speech recognition.First,equal width zoning line projection and binary width zoning line projection are carried out to the spectrogram,which are taken as the spectrogram of the first characteristic set and the second characteristic set,respectively.Meanwhile,equal width zoning line projection is carried out again to the spectrogram after Fourier transform,treating as the third feature set.Then,the above three feature sets are used as feature vectors to Support Vector Machine（SVM）as a classifier for the overall recognition of specific two words Chinese vocabulary.1000 voice samples are used in simulation experiment.The results show that the correct recognition rate of this method is 92.8%,and it provides a new way of thinking of Chinese vocabulary overall recognition.

关 键 词：通信技术 语音识别 语谱图 行投影 支持向量机 

分 类 号：TN912[电子电信—通信与信息系统]