摘要 |
In a speech data memory 60 speech data and symbol trains thereof are stored, and in a reference pattern memory 50 sets each of a given partial symbol train of a word presented for recognition and an index of speech data with the symbol train thereof containing the partial symbol train in the speech data memory 60 are stored. Speech recognition operation is executed on the basis of the read out data from the speech data memory 60 and the reference pattern memory 50.
|