Skip to main content
Fig. 5 | EURASIP Journal on Audio, Speech, and Music Processing

Fig. 5

From: ALBAYZIN 2018 spoken term detection evaluation: a multi-domain international evaluation in Spanish

Fig. 5

Example of the iterative DTW procedure: (1) The best match of q in x[1,n] is located in x[k1,k2]. (2) Since the score is greater than the established threshold T, the search continues in the surrounding segments x[1,k1−1] and x[k2+1,n]. (3) x[k2+1,n] is not searched, because it is too short. (4) The best match of q in x[1,k1−1] is located in x[k3,k4]. (5) But its score is lower than T, so the surrounding segments x[1,k3−1] and x[k4+1,k1−1] are not searched. The search procedure outputs the segments x[k1,k2] and x[k3,k4]

Back to article page