• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Conference on Speech Technology and Human-Computer Dialogue >Word error rate improvement and complexity reduction in Automatic Speech Recognition by analyzing acoustic model uncertainty and confusion
【24h】

Word error rate improvement and complexity reduction in Automatic Speech Recognition by analyzing acoustic model uncertainty and confusion

机译：通过分析声学模型不确定性和混淆来单词误差率改善和自动语音识别的复杂性降低

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

摘要

In this paper, a study about the uncertainty of the trained acoustic models and the confusion among these models is made in the context of speech recognition. The purpose is to find the most relevant voice features, hence the analysis is made on a per-feature basis. Model uncertainty is defined as a measure of feature distribution overlapping. A model is compared only to the models it is more similar to. Hence, confusion matrices are built from both feature distributions and recognition results. Next, the voice features are weighted according to their relevance in order to increase the discrimination among models, while relevance itself is deduced from the values of model uncertainty. Experimental results show that, by appropriate weighting, the recognition accuracy, in terms of Word Error Rate (WER), improves. Moreover, by removing the features with lower weights, the recognition accuracy is maintained, but the number of calculations is significantly reduced.
机译：在本文中，在语音识别的背景下，对训练有素的声学模型的不确定性以及这些模型中的混淆的研究。 目的是找到最相关的语音功能，因此分析是按每个特征的基础进行的。 模型不确定性被定义为特征分配重叠的量度。 仅将模型与其更类似于的模型进行比较。 因此，困惑矩阵由特征分布和识别结果构建。 接下来，根据其相关性来加权语音特征，以便增加模型之间的识别，而相关性本身将从模型不确定性的值推导出来。 实验结果表明，通过适当的加权，识别准确性在字错误率（WER）方面，改进。 此外，通过去除具有较低重量的特征，保持识别精度，但计算的数量显着降低。

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