...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Computer speech and language >Continuous Speech Recognition With Sparse Coding
【24h】

Continuous Speech Recognition With Sparse Coding

机译：稀疏编码的连续语音识别

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

Sparse coding is an efficient way of coding information. In a sparse code most of the code elements are zero; very few are active. Sparse codes are intended to correspond to the spike trains with which biological neurons communicate. In this article, we show how sparse codes can be used to do continuous speech recognition. We use the TIDIGITS dataset to illustrate the process. First a waveform is transformed into a spectrogram, and a sparse code' for the spectrogram is found by means of a linear generative model. The spike train is classified by making use of a spike train model and dynamic programming. It is computationally expensive to find a sparse code. We use an iterative subset selection algorithm with quadratic programming for this process. This algorithm finds a sparse code in reasonable time if the input is limited to a fairly coarse spectral resolution. At this resolution, our system achieves a word error rate of 19%, whereas a system based on Hidden Markov Models achieves a word error rate of 15% at the same resolution.
机译：稀疏编码是编码信息的有效方法。在稀疏代码中，大多数代码元素为零；很少有人活跃。稀疏代码旨在对应于与生物神经元进行通信的尖峰序列。在本文中，我们展示了稀疏代码如何用于进行连续语音识别。我们使用TIDIGITS数据集来说明该过程。首先，将波形转换成频谱图，然后通过线性生成模型找到频谱图的稀疏代码。通过使用尖峰序列模型和动态编程对尖峰序列进行分类。找到稀疏代码在计算上是昂贵的。对于此过程，我们使用带有二次编程的迭代子集选择算法。如果输入被限制在相当粗糙的光谱分辨率下，该算法会在合理的时间内找到稀疏代码。在此分辨率下，我们的系统可实现19％的单词错误率，而基于隐马尔可夫模型的系统在相同分辨率下可实现15％的单词错误率。

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