Lexical decision method was used to examine the effect of initial word frequency and last word frequency of Chinese idioms on the highly familiar idiom recognition time.
采用词汇判定法，考察首词频率和尾词频率对高熟悉度四字成语识别的影响。
Actually the kernel design in the recognition method based on discrete time - frequency representation is a problem of feature selection from the ambiguity functions to reduce feature dimension.
基于离散时频分布的信号识别方法，将时频核设计问题转化为以信号自模糊函数为原始特征的特征选择问题，以实现特征降维和信号识别。
In order to solve these problems, we proposed a single feature vector recognition model based on whole time-frequency information structure of digit speech.
为了解决这些问题，我们提出了基于数字语音时频信息整体结构的单特征向量识别模型。
应用推荐