| 摘要 |
A speech recognition apparatus of the speaker adaptation type operates to recognize inputted speech pattern produced by a particular speaker according to reference pattern produced by a standard speaker. The speech recognition apparatus is adapted to the particular speaker by converting the reference pattern to normalized pattern through learning operation using training pattern prodused provisionally by the particular speaker. In the alternative, the speech recognition apparatus is trained through conversion of the training pattern with reference to the reference pattern. The speech recognition apparatus operates to convert inputted speech pattern into normalized speech pattern in real time basis according to the result of learning operation and to recognize the normalized speech pattern according to the reference pattern. |
