Word recognition with HMM speech, model, using feature vector prediction from current feature vector and state control vector values

摘要

A pattern recognition technology includes a set of control signal vector and covariance matrix for respective states of a reference pattern of an objective word for recognition, which reference pattern is expressed by a plurality of states and transitions between the states, and transition probabilities between respective states. A prediction vector of t th feature vector is derived on the basis of the t-1 th feature vector and the control signal vector for the current (n th) state, determined beforehand for each of the states. A feature vector output probability for outputting the t th feature vector in n th state of the reference pattern of the objective word for recognition is derived from multi-dimensional gaussian distribution determined by the prediction vector and the covariance matrix with taking the prediction vector as an average vector. A word output probability for the reference pattern of the objective word, outputting the feature vector sequence of the input signal employing the feature vector output probability and transition probabilities contained in respective states of the reference pattern, is derived. One of the word output probabilities having the maximum probability as a result of recognition of the word among all of the word output probabilities derived with respect to the objective word is output.