Thresholds are determined by dynamic time warping (DTW) distance between training sequences and standard model.

然后计算训练序列与标准步态模型之间的动态时间规整距离，确定阈值。

youdao

In user-customized speaker verification system, we focused on building whole utterance model for every speaker and DTW, HMM and GMM modeling methods were adopted.

在用户定制密码的说话人认证系统中重点研究了为语音密码建立整句模型的方法，使用了DTW，HMM和GMM模型实现了对用户的建模和识别。

youdao