| 半监督矢量量化的汉语方言辨识 |
| |
| 引用本文： | 顾明亮,张彪. 半监督矢量量化的汉语方言辨识[J]. 计算机工程与应用, 2011, 47(33): 109-111. DOI: 10.3778/j.issn.1002-8331.2011.33.032 |
| |
| 作者姓名： | 顾明亮 张彪 |
| |
| 作者单位： | 1.徐州师范大学 物理与电子工程学院，江苏 徐州 2211162.江苏省语言科学与神经认知工程重点实验室，江苏 徐州 221116 |
| |
| 基金项目： | 国家社会科学基金重点资助项目(No.01AYY004); 江苏省“十五”社科基金资助项目(No.K3-013); 江苏省高校自然科学基金资助项目(No.99KJB510002); 徐州师范大学重大培育资助项目 |
| |
| 摘 要： | 提出了一种新的方言码本模型辨识系统。该方法利用半监督的思想对方言语音数据进行矢量量化，形成具有监督信息的码本模型。有效解决了在汉语方言辨识中码本精度不高的问题，系统的识别率有了很大提高。实验结果表明带有监督信息的码本量化方法明显优于传统LBG矢量量化方法，对于汉语三种方言，辨识率可达94.23%，比传统码本辨识系统提高了近13%的正确辨识率。
|
| 关 键 词： | 方言辨识 半监督码本 矢量量化 |
| 修稿时间： | |
Chinese dialect identification based on semi-supervised vector quantization |
| |
| GU Mingliang,ZHANG Biao. Chinese dialect identification based on semi-supervised vector quantization[J]. Computer Engineering and Applications, 2011, 47(33): 109-111. DOI: 10.3778/j.issn.1002-8331.2011.33.032 |
| |
| Authors: | GU Mingliang ZHANG Biao |
| |
| Affiliation: | 1.School of Physics and Electronic Engineering，Xuzhou Normal University，Xuzhou，Jiangsu 221116，China2.Jiangsu Key Lab of Language Science and Neural Cognitive，Xuzhou，Jiangsu 221116，China |
| |
| Abstract: | This paper presents a noval code model in Chinese dialect identification.This method takes advantage of semi-su-pervised thought to quantitate speech data and forms a code model with supervision information.It effectively solves the problem of low precision code and improves system recognition rate.Experimental results prove that the method with supervision information is superior to traditional LBG quantitation method.For three Chinese dialect,the system can achieve a high accuracy of 94.23% and raise the ... |
| |
| Keywords: | dialect identification semi-supervised code vector quantization
|
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《计算机工程与应用》浏览原始摘要信息 |
|
点击此处可从《计算机工程与应用》下载免费的PDF全文 |
