CodeForge

▍HMM training algorithm

space:nowrap;"> 隐马尔 柯夫模型( HM M ) 的传统 训练方法 ——Baum-W elch 算法只能 得到一个局 部最优 模型, 从而影 响 最终的识别率。对于 CHM M , 分段 K  平均方法来取得一个初始值可以解决这一问题, 但对 DHM M 却改进不大。 而...

▍Speaker recognition based on LPCC and MFCC

means algorithm and the BP neural network to sayWord recognition. The experimental results show that this method can effectively improve the recognition rate, but also to verify the robustness of MFCC parameters than LPCC parameters...