A set of consecutive digit time slots in which the position of each digit time slot can be identified by reference to a frame alignment signal. 一组连续的数字时间片段,每一数字时间片段在组内的位置可参考帧同步信号来标识。
By analyzing comparatively digit speech recognition models based on DTW structure with small training cor-pus, we point out their three general problems: ( 1) Such a DTW matching mode of one by one frame splits the internal relation within observation vector sequence. 本文通过对小训练样本集的基于DTW结构的数字语音识别模型的比较性分析,指出其存在的三个一般性问题:(1)DTW逐帧匹配模式割裂了观测向量序列的内在联系;