• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>IEEE International Meeting on Power, Electronics and Computing >Speech recognition using deep neural networks trained with non-uniform frame-level cost functions
【24h】

Speech recognition using deep neural networks trained with non-uniform frame-level cost functions

机译：语音识别使用具有非均匀帧级成本函数的深神经网络

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

摘要

The aim of this paper is to present two new variations of the frame-level cost function for training a deep neural network in order to achieve better word error rates in speech recognition. Minimization functions of a neural network are salient aspects to deal with when researchers are working on machine learning, and hence their improvement is a process of constant evolution. In the first proposed method, the conventional cross-entropy function can be mapped to a nonuniform loss function based on its corresponding extropy (a complementary dual function), enhancing the frames that have ambiguity in their belonging to specific senones (tied-triphone states in a hidden Markov model). The second proposition is a fusion of the proposed mapped cross-entropy and the boosted cross-entropy function, which emphasizes those frames with low target posterior probability. The developed approaches have been performed by using a personalized mid-vocabulary speaker-independent voice corpus. This dataset is employed for recognition of digit strings and personal name lists in Spanish from the northern central part of Mexico on a connected-words phone dialing task. A relative word error rate improvement of 12.3% and 10.7% is obtained with the two proposed approaches, respectively, regarding the conventional well-established crossentropy objective function.
机译：本文的目的是展示用于训练深度神经网络的帧级成本函数的两个新变化，以便在语音识别中实现更好的单词错误率。神经网络的最小化功能是处理研究人员在机器学习时处理的突出方面，因此它们的改进是一种不断发展的过程。在第一种提出的方​​法中，传统的跨熵函数可以基于其对应的外部内容（互补的双重功能）映射到非均匀损失函数，增强其属于特定Senones（Tied-Triphone状态）中具有模糊的帧一个隐藏的马尔可夫模型）。第二个命题是所提出的映射交叉熵和提升交叉熵函数的融合，其强调具有低目标后概率的框架。通过使用个性化中交扬声器 - 独立的语音语料库进行了开发的方法。此数据集用于在墨西哥北部的墨西哥北部的北部的墨西哥拨打电话拨号任务中识别数字字符串和个人名称列表。通过分别关于传统的良好成立的基于联语目标函数，通过两种提出的方​​法分别获得12.3×％和10.7 ％的相对字错误率改善。

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