Speech recognition using Dynamic Time Warping (DTW)

Abstract

Sound is one of the most common communication medias used by humans. Every human has different sound characteristics. To recognize the compatibility of a sound, a special algorithm is needed, which is Dynamic Time Warping (DTW). DTW is a method to measure the similarity of a pattern with different time zones. The smaller the distance produced, the more similar between the two sound patterns. Both sound patterns are similar, thus the two voices are said to be the same. The initial data on the speech recognition process is transformed into frequency waves. Pronounce volume, pronunciation time, and noise from the sound around the recording takes place affecting the distance generated. The smaller the effect, the smaller the distance that will be generated.