• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Speech Communication >Lattice segmentation and minimum Bayes risk discriminative training for large vocabulary continuous speech recognition
【24h】

Lattice segmentation and minimum Bayes risk discriminative training for large vocabulary continuous speech recognition

机译：大词汇量连续语音识别的格划分和最小贝叶斯风险判别训练

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

Lattice segmentation techniques developed for Minimum Bayes Risk decoding in large vocabulary speech recognition tasks are used to compute the statistics needed for discriminative training algorithms that estimate HMM parameters so as to reduce the overall risk over the training data. New estimation procedures are developed and evaluated for both small and large vocabulary recognition tasks, and additive performance improvements are shown relative to maximum mutual information estimation. These relative gains are explained through a detailed analysis of individual word recognition errors.
机译：为在大型词汇语音识别任务中进行最小贝叶斯风险解码而开发的格划分技术用于计算估计HMM参数的判别训练算法所需的统计信息，从而降低训练数据的总体风险。针对大小词汇识别任务开发和评估了新的估计程序，并显示了相对于最大互信息估计的累加性能改进。通过对单个单词识别错误的详细分析来解释这些相对增益。

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