Figure 3.

Percent agreement between automatic forced-alignment algorithms and human aligners. Each point represents the percentage of agreement for an alignment algorithm and a human aligner for one child. Points are colored to uniquely identify children. There were two human aligners, so each child appears twice per row (two points of same color). Vertical bar marks the median in that row. Ages in months were 39 (blue circles), 40 (green squares), 52 (orange diamonds), and 66 (red triangles). MFA = Montreal Forced Aligner; SAT = speaker adaptive training; P2FA = Penn Phonetics Lab Forced Aligner.