摘要
该文提出了一种基于基音频率特征的中国朝鲜族语言、韩国朝鲜语和朝鲜朝鲜语方言的自动辨识方法。首先,选择具有良好区分度的基频移位差分系数作为三个方言的特征参数;其次,设计和采用了分层支持向量机分类器,并进一步引入投票法确定最佳的分类结果。实验结果表明该文提取的特征参数具有良好的区分性和较强的稳定性,该文提出的方言辨识方法比传统的移位差分倒谱系数特征方法识别率高,可以有效解决朝鲜朝鲜语、韩国朝鲜语和中国朝鲜族语言的方言辨识问题。
This paper presents a pitch-based automatic recognition method of China＇s Korean, Republic of Korea and DPRK Korean dialects. Firstly, the shifted delta coefficients of pitch is extracted as feature parameter because of its strong discriminability. Secondly, the layered SVM algorithm and a voting mechanism are adopted to get the optimal classification result. Experimental results show that the recognition rate of the proposed method is better than conventional method based on shifted delta cepstral coefficients.
出处
《中文信息学报》
CSCD
北大核心
2017年第2期55-60,70,共7页
Journal of Chinese Information Processing
基金
吉林省科技厅自然科学基金(20140101225JC)
关键词
方言辨识
语种辨识
基频特征
移位差分系数
支持向量机
dialect identification
language identification
pitch feature
shifted delta cepstral coefficients
support vector machine
