摘要 |
A speech model preparing method capable of easily preparing a new Hidden Marcov Model (HMM) of an input speech with a very small number of utterances such as once or twice , and a speech recognition apparatus using this method. A speech recognition apparatus uses, as a speech model, a continuous distribution type HMM defined by three parameters of a state transition probability, an average vector and a variance. The apparatus computes (7) an average vector of an input speech to be learned, selects an HMM approximate to the input to-be-learned speech as an initial model from a registration dictionary (3), replaces at least an average vector of the selected HMM with the computed average vector of the to-be-learned speech and adds an obtained HMM as an HMM for the input to-be-learned speech in the dictionary (3). <IMAGE> |