DTW algorithm using Speaker Recognition 说明利用DTW算法进行说话人识别
Both analysis and experiments show that the recognition time is proportional to the square of the length of the feature vector, if dynamic time warping (DTW) algorithm is employed in recognition.
分析和实验结果表明:若采用动态时间规正算法(DTW),识别时间与特征矢量长度的平方成正比关系。
TMS320VC5416 16-bit fixed-point DSP is adopted in its core processor of the hardware. Dynamic Time Warping (DTW) algorithm is chiefly used to implement the software.
系统硬件的核心芯片采用普遍使用的16位定点DSP芯片TMS320 VC 5416,软件上主要采用动态时间规整算法来实现语音识别。
应用推荐