隐Markov模型(简称为HMM)是在Markov模型的基础上发展而来的。由于实际问题比Markov模型所描述的问题更为复杂，观测到事件并不是与状态一一对应，而是通过一组观测概率分布相联系，这样的模型称为HMM。它是一个双重随机过程，其中之一是Markov链，这是一个基本的随机过程，描述状态之间的转移。另一个随机过程描述状态和观测变量之间的统计对应关系，这样，站在观察者的角度，只能看到观察值，不象Markov模型中的观测值和状态一一对应。(The implicit Markov model (HMM) is developed on the basis of the Markov model. Since the actual problems are more complex than those described by the Markov model, the observed events do not correspond to States, but are connected by a set of observation probability distributions. Such models are called HMM. It is a doubly stochastic process, one of which is the Markov chain, which is a basic stochastic process that describes the transfer between states. Another stochastic process describes the statistical correspondence between the state and the observed variables, so that the observer can only see the observations at the observer's point of view, unlike the observed values and states in the Markov model.)