计算机工程与应用2017，Vol.53Issue(17)：160-165,6.DOI:10.3778/j.issn.1002-8331.1610-0315
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
摘要
Abstract
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 typ-ical language with a tone and Chinese dialects have obvious differences among rhythm, stress and other rhythmic struc-ture. 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 is 8.01％, which is 56.2％lower than the Gaussian Mixture Model-Universal Background Model(GMM-UBM)method. The experimental re-sults show that the I-vector method fusing global prosodic information can improve the Chinese dialects identification ac-curacy effectively.关键词
汉语方言辨识/韵律特征/I-vector/特征融合Key words
Chinese dialects identification/prosodic features/I-vector/features fusion分类
信息技术与安全科学引用本文复制引用
邱远航,顾明亮,马勇,金赟,韩军,赵冬梅,赵呈昊..全局信息融合的汉语方言自动辨识[J].计算机工程与应用,2017,53(17):160-165,6.基金项目
国家自然科学基金(No.61040053,No.61673196) （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) （No.2012JDXM016）
江苏省普通高校研究生科研创新计划项目(No.KYLX15_1463). （No.KYLX15_1463）
