| 摘要 |
Speech recognition in prior art uses one extracted characteristic component (xi) to represent one phoneme (Xi) as spoken by one speaker. This invention provides for recognizing the same phoneme as spoken by different speakers, by deriving a group of such components (xik), each a slight variant of the others, to allow finding one component most similar to both the specific phoneme and specific speaker, the method comprising the steps of: normalizing the sound pressure level of an input speech from an unknown speaker; analyzing the normalized voice in a plurality of channels having different frequencies; setting, with respect to the output Fj of each frequency band thus analyzed, a weight alpha j of the output Fj so that weight alpha j corresponds to a characteristic of a predetermined phoneme Xi; extracting the characteristic component xi of the phoneme Xi, setting a weight beta j of output Fj so that, when the extracted characteristic component xi causes a malfunction or error due to another phoneme Xe, a characteristic of phoneme Xe is corresponded to; simultaneously extracting the characteristic component xe of phoneme Xe and, when the difference between the characteristic components thus extracted is greater than a predetermined threshold value gamma i, applying the difference as a characteristic parameter for the phoneme xi; expanding the characteristic parameter to obtain a characteristic parameter group based on the characteristic parameter, each being slightly different from each other so as to be adapted for individual characteristics of different speakers; subsequently extracting from the characteristic parameter group a characteristic parameter, having maximum similarity to a reference parameter previously memorized, as an adaptive parameter adaptive to the unknown speaker; and, matching a standard pattern derived from the extracted adaptive parameters with an unknown pattern corresponding to the unknown speakers, thereby effecting recognition or analysis of the voice. |
