语音机器人隐马尔可夫算法探究  

Research on Hidden Markov Algorithm for Speech Robot

作　　者：黄哲彬 HUANG Zhebin(North China University of Water Resources and Electric Power School of Information Engineering,Zhengzhou 450046,Chin)

机构地区：[1]华北水利水电大学信息工程学院,河南郑州450046

出　　处：《现代信息科技》2018年第4期95-96,98,共3页Modern Information Technology

摘　　要：一直以来,人们在探索一种人与机器交流的方法。随着科学技术的飞速发展,语音机器人的出现,实现了真正意义上的人机交流。隐马尔可夫模型(HMM)作为非特定语音识别系统的主流技术在语音机器人系统中被广泛地使用。传统的隐马尔可夫模型由于初始化方法过于简单,精度和速度都达不到预期结果。实验证明,改进语音特征参数相邻帧相关性的隐马尔可夫模型初始化算法能有效地解决这一问题。All along,people are exploring a way of communication between people and machines. With the rapid development of science and technology,the emergence of the voice robot has realized the real sense of man machine communication. Hidden Markov Model（HMM）is widely used in speech robot system as the mainstream technology of non specific speech recognition system. Because the initialization method is too simple for the traditional HMM,the accuracy and speed are not as good as expected. Experiments show that the HMM initialization algorithm with improved speech feature parameters and adjacent frames can effectively solve this problem.

关 键 词：非特定人语音识别 隐马尔可夫模型 初始化算法 

分 类 号：TN912.34[电子电信—通信与信息系统]