Skip to main content

Table 6 Correct identification rates for alternating sections.

From: A Decision-Tree-Based Algorithm for Speech/Music Classification and Segmentation

Signal

Speech

Music

Total duration(sec)

960 seconds

960 seconds

Total error(sec)

7.01

13.73

Correct identification

98.8%

98.6%

Average latency

4.01 (std = 0.51)

5.13 (std = 0.71)