Abstract: A Chinese dialect identification system based on a mixed SOM neural network and SVM is proposed in this paper.Hunan dialects have been selected as the research object.SOM is applied to cluster for the MFCC of various dialects，and SVM is used as the final implement of decision and identification.The results show that this system has better real-time property and identification rate than the conventional methods especially at a low signal-to-noise ratio.

Key words: dialect identification, SOM neural network, Support Vector Machine（SVM）

摘要： 建立了一个基于SOM神经网络和支持向量机（SVM）的汉语方言辨识系统。该系统以湖南方言作为研究对象，借助SOM神经网络对不同方言的MFCC特征参量进行聚类，并用SVM作为最终的决策辨识器。实验结果表明：该系统与传统系统相比实时性和辨识率较好，特别适用于信噪比低的情况。

关键词: 方言辨识, SOM神经网络, 支持向量机