Speech recognition apparatus and method adapting best transformation function to transform one of the input speech and acoustic model

The present invention relates to a speech recognition apparatus for recognizing speeches of a plurality of users with high accuracy. An adapting unit detects a best transformation function for adapting an input speech to an acoustic model from at least one transformation function based on the transformation results which are obtained by transforming the input speech by at least one transformation function stored in a storing unit and allocates the input speech to the best transformation function. Further, the adapting unit updates the transformation function to which the new input speech is allocated by all the input speeches allocated to the transformation function. A selecting unit selects the transformation function used for transforming the input speech from at least one transformation function stored in the storing unit A transforming unit transforms the input speech by the selected transformation function. A matching unit performs matching processing in which the speech obtained by transforming the input speech matches the acoustic model. The present invention can be applied to speech recognition apparatuses.