摘要 |
The present invention relates to a pre-processing apparatus for voice recognition and a method thereof. The apparatus includes: a trailing silence section detection unit which detects the length of a trailing silence section included in a voice signal; a reference trailing silence section storage unit storing the length of a reference trailing silence section; and a trailing silence section adjusting unit which adjusts the length of the trailing silence section included in the voice signal to match the length of the reference trailing silence section. |