...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>The European Journal of Neuroscience >Applying independent component analysis to detect silent speech in magnetic resonance imaging signals.
【24h】

Applying independent component analysis to detect silent speech in magnetic resonance imaging signals.

机译：应用独立分量分析来检测磁共振成像信号中的无声语音。

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

Independent component analysis (ICA) can be usefully applied to functional imaging studies to evaluate the spatial extent and temporal profile of task-related brain activity. It requires no a priori assumptions about the anatomical areas that are activated or the temporal profile of the activity. We applied spatial ICA to detect a voluntary but hidden response of silent speech. To validate the method against a standard model-based approach, we used the silent speech of a tongue twister as a 'Yes' response to single questions that were delivered at given times. In the first task, we attempted to estimate one number that was chosen by a participant from 10 possibilities. In the second task, we increased the possibilities to 1000. In both tasks, spatial ICA was as effective as the model-based method for determining the number in the subject's mind (80-90% correct per digit), but spatial ICA outperformed the model-based method in terms of time, especially in the 1000-possibility task. In the model-based method, calculation time increased by 30-fold, to 15 h, because of the necessity of testing 1000 possibilities. In contrast, the calculation time for spatial ICA remained as short as 30 min. In addition, spatial ICA detected an unexpected response that occurred by mistake. This advantage was validated in a third task, with 13 500 possibilities, in which participants had the freedom to choose when to make one of four responses. We conclude that spatial ICA is effective for detecting the onset of silent speech, especially when it occurs unexpectedly.
机译：独立成分分析（ICA）可有效地应用于功能成像研究，以评估与任务相关的大脑活动的空间范围和时间分布。它不需要关于被激活的解剖区域或活动的时间分布的先验假设。我们应用空间ICA来检测无声语音的自愿但隐藏的响应。为了针对基于标准模型的方法验证该方法，我们使用绕口令的无声语音作为对在指定时间传递的单个问题的“是”响应。在第一个任务中，我们尝试估计参与者从10种可能性中选择的一个数字。在第二个任务中，我们将可能性增加到1000。在这两个任务中，空间ICA都与确定对象头脑中数字的基于模型的方法一样有效（每位数字正确率为80-90％），但是空间ICA的效果优于时间上基于模型的方法，尤其是在1000可能性任务中。在基于模型的方法中，由于需要测试1000种可能性，因此计算时间增加了30倍，达到15小时。相比之下，空间ICA的计算时间仍然短至30分钟。此外，空间ICA检测到意外发生的错误响应。在第三项任务中验证了这一优势，有13 500种可能性，参与者可以自由选择何时做出四个响应之一。我们得出结论，空间ICA对于检测无声语音的发作是有效的，尤其是在意外发生时。

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