• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International Conference on Cognitive Informatics and Soft Computing >Isolated Word Recognition Based on Different Statistical Analysis and Feature Selection Technique
【24h】

Isolated Word Recognition Based on Different Statistical Analysis and Feature Selection Technique

机译：基于不同统计分析和特征选择技术的孤立的词识别

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Isolated word recognition serve as an important aspect of speech recognition problem. This paper contributes a solution of speaker-independent isolated word recognition based on different statistical analysis and feature selection method. In this work different parametric and nonparametric statistical algorithm such as analysis of variance (ANOVA) and Kruskal-Wallis are used to rank the features and incremental feature selection (IFS) to find the efficient features set. The objective of applying statistical analysis algorithm and feature selection technique on the cepstral feature is to improve the word recognition performance using efficient and optimal number of feature set. The experimental analysis is carried out using two machine learning techniques such as Artificial Neural Network (ANN) and Support vector machine (SVM) classifier. Performance of both the classifier has been evaluated and described in this paper. From the experimental analysis it has been observed that statistical analysis with feature selection technique provides better result for the two classifier as compared to original all cepstral features.
机译：孤立的词识别作为语音识别问题的一个重要方面。本文有助于基于不同统计分析和特征选择方法的扬声器无关的隔离字识别解决方案。在这项工作中，不同的参数和非参数统计算法，例如方差分析（ANOVA）和Kruskal-Wallis用于对特征和增量特征选择（IFS）进行排序，以找到所需的功能。应用统计分析算法和特征选择技术对临时谱特征的目的是使用有效和最佳的特征集来改善单词识别性能。使用两种机器学习技术（如人工神经网络（ANN）和支持向量机（SVM）分类器进行实验分析。本文已经评估和描述了两种分类器的性能。从实验分析开始，已经观察到具有特征选择技术的统计分析为两个分类器提供更好的结果，与原版所有临时特征相比。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号