| 摘要 |
Each word to be recognized is represented by gender-specific hidden Markov models and output probability functions and transition probabilities preset in the gender-specific hidden Markov models are prestored in a ROM 6. With reference to feature parameters detected by a feature value detector 3 and to the hidden Markov models, a speech recognizer 4 determines an occurrence probability of a feature parameter sequence. In the process of determining the occurrence probability, the speech recognizer 4 gives each word a state sequence of one hidden Markov model common to the gender-specific hidden Markov models, multiplies each preset pair of an output probability function value and a transition probability together among the output probability functions and transition probabilities stored in the ROM 6, selects the largest product as the probability of each state of the common hidden Markov model, determines the occurrence probability based on the selected product, and then recognizes the input speech based on the occurrence probability thus determined. <IMAGE>
|
