• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>European Conference on Speech Communication and Technology v.3; 20010903-20010907; Aalborg; DK >On the Choice of Classes in MCE based discriminative HMM-Training for Speech Recognizers used in the Telephone Environment
【24h】

On the Choice of Classes in MCE based discriminative HMM-Training for Speech Recognizers used in the Telephone Environment

机译：基于MCE的歧视性HMM训练中用于电话环境的语音识别器的类选择

获取原文
获取原文并翻译 | 示例
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

One of the most commonly used discriminative approaches in parameter estimation for Hidden Markov Models is the Minimum Classification Error (MCE) method ([1]). This paper studies possible choices for the classes (i.e. basic speech units) in MCE training and their application for several tasks suitable for speech driven dialog systems in the telephone environment. The considered choices of classes are HMM states, phonemes, words and sequences of words. The theoretical suitability and practical considerations for the different criteria are discussed. Using the different training criteria consistent experimental results are given for four tasks: non-task-specific training, training for small vocabulary isolated word recognition, training for connected digit recognition and for letter recognition. In all experiments not only the objective of the optimization but also the resulting word recognition performance is investigated. It shows that for the given setup only word and word string based criteria are capable to reduce the word error rate.
机译：隐马尔可夫模型参数估计中最常用的判别方法之一是最小分类误差（MCE）方法（[1]）。本文研究了MCE培训中的班级（即基本语音单元）的可能选择及其在适合电话环境中语音驱动对话系统的多项任务中的应用。考虑的类别选择是HMM状态，音素，单词和单词序列。讨论了不同标准的理论适用性和实际考虑因素。使用不同的培训标准，可以为四个任务提供一致的实验结果：非任务特定的培训，小词汇孤立单词识别的培训，连接数字识别和字母识别的培训。在所有实验中，不仅要研究优化的目的，还要研究由此产生的单词识别性能。它表明，对于给定的设置，仅基于单词和单词字符串的标准能够降低单词错误率。

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