Skip to main content

Table 5 Accuracy performance of the auto-context algorithm using contextual information from different locations

From: Exploiting contextual information for prosodic event detection using auto-context

Auto-context (%)

None

Preceding

Following

Both

Two-way (M=3)

79.3

80.4

80.1

81.2 (M=3 itr = 3)

Four-way (M=2)

74.2

75.3

75.0

75.7 (M=2 itr = 6)

  1. Here, ‘None’ means not using auto-context, and ‘Preceding’, ‘Following’, and ‘Both’ refer to the directions of contextual prosodic information.