-
公开(公告)号:KR1019930005772B1
公开(公告)日:1993-06-24
申请号:KR1019900018942
申请日:1990-11-22
Applicant: 한국전자통신연구원
IPC: G06F15/18
Abstract: The hidden markov model (HMM) for processing the time sequence pattern comprises: a model parameter register (2), which stores a parameter of the state transition matrix (A), a parameter of the observation probability density function (B) and a parameter (F) indicating the initial distribution of state; a start model selecting section (1), which satisfys the condition of M0=(A0,B0,π0) by selectiong the arbituary parameter (A0,B0,π0) from the parameter register; a state sequence separating section (3), which match the syllable signal inputted from the learning data input section (4) with the parameter (A0,B0,π0) inputted from the section (1); a parameter reestimation section (5), which looks for a new parameter (An,Bn,Tn).
Abstract translation: 用于处理时间序列模式的隐马尔可夫模型(HMM)包括:模型参数寄存器(2),其存储状态转移矩阵(A)的参数,观察概率密度函数(B)的参数和参数 (F)表示状态的初始分布; 通过从参数寄存器中选择仲裁参数(A0,B0,π0),启动模型选择部分(1)满足M0 =(A0,B0,π0)的条件; 将从学习数据输入部分输入的音节信号与从部分(1)输入的参数(A0,B0,π0)相匹配的状态序列分离部分(3); 参数重新估计部分(5),其寻找新的参数(An,Bn,Tn)。
-