| 基于纠错输出编码的支持向量机在语音识别中的应用 |
| |
| 引用本文： | 刘晓峰,张雪英.基于纠错输出编码的支持向量机在语音识别中的应用[J].太原理工大学学报,2011,42(1):34-37. |
| |
| 作者姓名： | 刘晓峰 张雪英 |
| |
| 作者单位： | 1. 太原理工大学,理学院,太原,030024
2. 太原理工大学,信息工程学院,太原,030024 |
| |
| 基金项目： | 国家自然科学基金(61072087/F010406); 山西省自然科学基金(20100110201); 太原理工大学青年基金(900103-03020669) |
| |
| 摘 要： | 利用纠错输出编码的矩阵编码构造出若干个无关的子支持向量机,用来改善分类模型的整体容错性能。使用了一对余、一对一、稠密型随机编码、稀疏型随机编码4种常用的纠错输出编码方法,用于训练集和测试集。实验结果显示,对于韩语非特定人小词汇量孤立词的语音识别,基于纠错输出编码的支持向量机比隐马尔科夫方法具有更高的识别率。其中,一对一编码是效果最好的。
|
| 关 键 词： | 语音识别 支持向量机 纠错输出编码 |
Speech Recognition Based on Support Vector Machine and Error Correcting Output Codes |
| |
| LIU Xiao-feng,ZHANG Xue-ying.Speech Recognition Based on Support Vector Machine and Error Correcting Output Codes[J].Journal of Taiyuan University of Technology,2011,42(1):34-37. |
| |
| Authors: | LIU Xiao-feng ZHANG Xue-ying |
| |
| Institution: | LIU Xiao-fenga,ZHANG Xue-yingb(a.College of Sciences,b.College of Information Engineering,TUT,Taiyuan 030024,China) |
| |
| Abstract: | A method was proposed based on application of Error Correcting Output Codes Support Vector Machine(ECOC-SVM) in order to get better results of speech recognition.Some uncorrelated SVMs were constructed based on ECOC matrix codes to improve the integrated performance of fault tolerance of classification model.This paper gives four commonly used encodings of ECOC: One versus the rest,One versus one,Dense random and Sparse random.By comparing the results with these of speech recognition based on Hidden Markov ... |
| |
| Keywords: | Speech Recognition Support Vector Machine Error Correcting Output Code |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
