基于多尺度熵和遗传算法改进的语音识别技术  

Improved speech recognition technology based on multi-scale entropy and genetic algorithm

作　　者：樊海花 穆春阳 马行[1] FAN Haihua;MU Chunyang;MA Xing(Institute of Information and Communication Technology,North Minzu University,Yinchuan 750021,China;College of Mechatronic Engineering,North Minzu University,Yinchuan 750021,China)

机构地区：[1]北方民族大学信息与通信技术研究所,宁夏银川750021 [2]北方民族大学机电工程学院,宁夏银川750021

出　　处：《现代电子技术》2019年第6期126-131,共6页Modern Electronics Technique

基　　金：国家自然科学基金(61163002);国家民委中青年英才培养计划(2016GQR10);宁夏自然科学基金(NZ16086);宁夏回族自治区高等学校科技创新平台:先进装备关键零部件及系统创新产学研合作基地;北方民族大学研究生创新项目(YCX1771)资助~~

摘　　要：现代语音识别系统大多数都处在复杂的环境中,语音特征的提取势必会受到噪声的影响;在低信噪比环境下的隐马尔可夫模型,它的训练参数容易收敛于局部最小值,导致识别率下降。首先对采集到的语音信号,利用补充的总体经验模态分解(CEEMD)和多尺度熵算法对信号进行随机性检测,该方法在检测出CEEMD分解的异常分量后,进行经验模态分解(EMD);其次将分解得到的近乎纯净的语音信号,作为基于遗传算法改进的隐马尔可夫模型的输入。实验结果表明,利用多尺度熵与遗传算法改进的隐马尔可夫模型相结合的方式,具有更优的收敛速度和优化性能,识别率至少提高1.23%。The training parameters of the hidden Markov model in the low signal-to-noise ratio environment tend to converge to local minimum values,resulting in recognition rate decline.Therefore,the complementary ensemble empirical model decomposition(CEEMD)and multi-scale entropy algorithm are used to conduct random detection of the collected speech signals.In the method,the empirical model decomposition(EMD)is conducted after detecting the abnormal components decomposed by the CEEMD.The near-pure speech signals obtained by decomposition are taken as the input of the improved hidden Markov model based on the genetic algorithm.The experimental results show that the mode combining the multi-scale entropy and hidden Markov model improved by the genetic algorithm has a good convergence speed and optimization performance,and its recognition rate is increased by at least 1.23%.

关 键 词：模态分解 语音识别 局部收敛 多尺度熵 隐马尔可夫模型 遗传算法 

分 类 号：TN912.3-34[电子电信—通信与信息系统]