Table 3.
Counts of frames given human analysts’ classifications (rows) and LENA classifications (columns). Percentages are given reflecting the number of frames assigned one or more specific labels by LENA, divided by the total number of frames within that human classification category. Percentage values across rows thus sum to 100% (with any deviations due to rounding).
| LENA Classifications | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
|
| ||||||||||
| FAN | MAN | CHN or CXN | NON | OLN | TVN | FUZ | SIL or “faint” | Totals | ||
| Human classifications | female adult speech | 46011 (59%) | 3951 (5%) | 9068 (12%) | 249 (0%) | 5954 (8%) | 1264 (2%) | 574 (7%) | 5126 (7%) | 77370 |
| male adult speech | 6770 (18%) | 21790 (57%) | 1482 (4%) | 46 (0%) | 2151 (6%) | 895 (2%) | 2768 (7%) | 2182 (6%) | 38084 | |
| child vocalization | 4561 (7%) | 399 (1%) | 41908 (63%) | 355 (1%) | 7481 (11%) | 565 (1%) | 3878 (6%) | 7011 (11%) | 66158 | |
| other | 11400 (4%) | 8855 (3%) | 27715 (11%) | 2603 (1%) | 18781 (7%) | 6777 (3%) | 40284 (16%) | 14277 5 (55%) | 25919 0 | |
|
| ||||||||||
| Totals | 68742 | 34995 | 80173 | 3253 | 34367 | 9501 | 52677 | 15709 4 | 44080 2 | |
Note. Counts in boldface font were considered correct classifications.