摘要 |
Disclosed in the present invention are an apparatus and a method for preprocessing a voice signal. According to one embodiment of the present invention, the method for preprocessing a voice signal includes the following steps: extracting at least one frame corresponding to a voice recognition range among a plurality of frames forming the voice signal; and generating a complementary frame which complements voice recognition for the voice recognition range based on the at least one frame and outputs the voice signal along with the frames. |