• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Computer speech and language >Speech recognition with unknown partial feature corruption ― a review of the union model
【24h】

Speech recognition with unknown partial feature corruption ― a review of the union model

机译：具有未知部分特征损坏的语音识别-联合模型的回顾

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

This paper provides a summary of our studies on robust speech recognition based on a new statistical approach ― the probabilistic union model. We consider speech recognition given that part of the acoustic features may be corrupted by noise. The union model is a method for basing the recognition on the clean part of the features, thereby reducing the effect of the noise on recognition. To this end, the union model is similar to the missing feature method. However, the two methods achieve this end through different routes. The missing feature method usually requires the identity of the noisy data for noise removal, while the union model combines the local features based on the union of random events, to reduce the dependence of the model on information about the noise. We previously investigated the applications of the union model to speech recognition involving unknown partial corruption in frequency band, in time duration, and in feature streams. Additionally, a combination of the union model with conventional noise-reduction techniques was studied, as a means of dealing with a mixture of known or trainable noise and unknown unexpected noise. In this paper, a unified review, in the context of dealing with unknown partial feature corruption, is provided into each of these applications, giving the appropriate theory and implementation algorithms, along with an experimental evaluation.
机译：本文提供了基于新的统计方法-概率联合模型的鲁棒语音识别研究的摘要。考虑到部分声学特征可能被噪声破坏，我们考虑语音识别。联合模型是一种基于特征的干净部分进行识别的方法，从而减少了噪声对识别的影响。为此，联合模型类似于缺失特征方法。但是，这两种方法通过不同的途径来达到此目的。缺失特征方法通常需要识别噪声数据以去除噪声，而并集模型则基于随机事件的并集组合局部特征，以减少模型对有关噪声信息的依赖性。我们先前研究了联合模型在语音识别中的应用，该语音识别涉及频带，持续时间和特征流中未知的部分损坏。此外，研究了联合模型与常规降噪技术的组合，以此作为处理已知或可训练噪声与未知意外噪声的混合物的方法。在本文中，在处理未知的部分特征损坏的情况下，对每个应用程序进行了统一的审查，并给出了适当的理论和实现算法以及实验评估。

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