摘要 |
PROBLEM TO BE SOLVED: To more precisely recognize voice. SOLUTION: A notation character string outputted from a voice data conversion means 5 is stored in a non-decided character string storage means 12 in a non-decided state and a read character string is stored in a read character string storage means 11. An output means 18 outputs a display control instruction so that a notation character string stored in the non-decided character string storage means 12 is displayed in a display means 19 in a non-decided state. When a conversion instruction on the noticed part of the notation character string stored in the non-decided character string storage means 12 is given, a manual conversion means 13 executes conversion based on the instruction. Thus, precise recognition can be executed by changing the part based on the recognized conversion instruction of an operator. |