I am trying to output the pdf sequences for an utterance using the -p flag of HMGenS tool. However, when I checked the .lf0_pdf file I found the following values.
2.108878e+02 0.000000e+00 0.000000e+00
4.526616e+01 0.000000e+00 0.000000e+00
2.108878e+02 -5.418909e+01 5.599444e-01
4.526616e+01 2.456803e+03 4.348116e+02
3.033320e+02 -4.598551e+01 2.942826e+00
6.523090e+01 4.490591e+03 1.066298e+03
3.033320e+02 -4.598551e+01 2.942826e+00
6.523090e+01 4.490591e+03 1.066298e+03
3.033320e+02 -4.598551e+01 2.942826e+00
6.523090e+01 4.490591e+03 1.066298e+03
4.374781e+02 6.018007e+01 1.525493e+00
9.478203e+01 7.552817e+03 1.075918e+03
4.374781e+02 6.018007e+01 1.525493e+00
9.478203e+01 7.552817e+03 1.075918e+03
4.374781e+02 0.000000e+00 0.000000e+00
9.478203e+01 0.000000e+00 0.000000e+00
-1.000000e+10 -1.000000e+10 -1.000000e+10
-1.000000e+10 -1.000000e+10 -1.000000e+10
-1.000000e+10 -1.000000e+10 -1.000000e+10
-1.000000e+10 -1.000000e+10 -1.000000e+10
-1.000000e+10 -1.000000e+10 -1.000000e+10
-1.000000e+10 -1.000000e+10 -1.000000e+10
-1.000000e+10 -1.000000e+10 -1.000000e+10
-1.000000e+10 -1.000000e+10 -1.000000e+10
I think the first line is the mean of static and dynamic features and the second line is the variance? but the values of the mean are too high, do they represent F0, logF0 or some other scaling is used? What do they correspond to in terms of fundamental frequency in Hz? The sampling rate is 48000.
Regards,
Najeeb