全局信息融合的汉语方言自动辨识  

Automatic identification of Chinese dialects based on global infor-mation fusion

作　　者：邱远航[1] 顾明亮[1] 马勇[1] 金赟[1] 韩军[1] 赵冬梅[1] 赵呈昊 QIU Yuanhang;GU Mingliang;MAYong;JIN Yun;HAN Jun;ZHAO Dongmei;ZHAO Chenghao(School of Physics and Electronic Engineering, Jiangsu Normal University, Xuzhou, Jiangsu 221116, China;School of Electrical Engineering & Automation, Jiangsu Normal University, Xuzhou, Jiangsu 221116, China)

机构地区：[1]江苏师范大学物理与电子工程学院,江苏徐州221116 [2]江苏师范大学电气工程及自动化学院,江苏徐州221116

出　　处：《计算机工程与应用》2017年第17期160-165,共6页Computer Engineering and Applications

基　　金：国家自然科学基金(No.61040053;No.61673196);江苏省高校哲学社会科学重点研究基地重大项目(No.2012JDXM016);江苏省普通高校研究生科研创新计划项目(No.KYLX15_1463)

摘　　要：提出身份认证矢量(Identity vector,I-vector)结合韵律信息的汉语方言辨识方法。全差异空间替代本征音与本征信道空间,将高维超矢量映射为低维I-vector表示,并进行信道补偿与特征降维处理。汉语是有调语言,各方言在其韵律结构上具有明显差异,I-vector特征融合全局韵律信息,可有效增补各方言鉴别性。利用融合信息对闽、粤、吴等五种方言以及普通话进行辨识实验,等错率(Equal Error Rate,EER)达到8.01%,比高斯混合模型-通用背景模型(Gaussian Mixture Model-Universal Background Model,GMM-UBM)降低56.2%,表明融合全局韵律信息的Ivector方法可有效提高汉语方言辨识正确率。A new method of Chinese dialects identification based on Identity vector(I-vector)combined with prosodic information is proposed.The high-dimensional super-vector is mapped to a low-dimensional I-vector representation by Total Variability(TV)model.Channel compensation and feature dimension reduction are also performed.Chinese is a typical language with a tone and Chinese dialects have obvious differences among rhythm,stress and other rhythmic structure.The serial fusion of I-vectors with global prosodic information can improve the distinguishability of Chinese dialects effectively.The Equal Error Rate(EER)using fusion strategy of five Chinese dialects and Mandarin is8.01%,which is56.2%lower than the Gaussian Mixture Model-Universal Background Model(GMM-UBM)method.The experimental results show that the I-vector method fusing global prosodic information can improve the Chinese dialects identification accuracy effectively.

关 键 词：汉语方言辨识 韵律特征 I-vector 特征融合 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]