HTS version 2.1 includes hidden semi-Markov model (HSMM) training/adaptation/synthesis, speech parameter generation algorithm considering global variance (GV), SMAPLR/CSMAPLR adaptation, and other minor new features.

These marks, obtained by listening to several speech sequences, are then used to calculate average results for each of the features listed above, thus providing a global estimate of the behavior of the VAD being tested. To conclude, whereas objective

根据图像的全局对比度进行视觉的显著性区域检测，该算法较经典算法更快更准确。-According significant global contrast of the image area is detected visually, the algorithm faster and more accurate than the classical algorithm.