# [hts-users:03239] duration modeling and dur file

 Hello, I am using HTS-2.2 for Speaker adaptation. In HMGenS after adaptation, the output files are mgc, lf0, bap, dur. And I found that mgc, lf0, bap are generated through dur file.In the paper, Hidden Semi-Markov Model Based Speech Synthesis System, I’ve understood that state durations are, after all, determined by state duration mean vector. So I expected that the mean of *.dur file is same as a mean vector of duration model.However, the mean in the *.dur file is little different from a mean of duration model, for example, 1.313743e+00 is mean of * .dur file, 1.306419e+00 is mean of duration model.Why it is different? Is there another algorithm to generate duration mean vector or something wrong with this process? And more important problem is that sometimes the duration is set to “1” for all states without considering the mean.Below is the problem, and this problem does not appear in the speech without adaptation. Why does this problem occurs? *.durAX^P-WW+L=R@2_2/A:2/B:3-2-&14-20|WW/C:2/D:2/E:3+&7/F:4/H:12=33.state[2]: duration=1 (frame), mean=1.313743e+00AX^P-WW+L=R@2_2/A:2/B:3-2-&14-20|WW/C:2/D:2/E:3+&7/F:4/H:12=33.state[3]: duration=1 (frame), mean=2.475758e+00AX^P-WW+L=R@2_2/A:2/B:3-2-&14-20|WW/C:2/D:2/E:3+&7/F:4/H:12=33.state[4]: duration=1 (frame), mean=3.064046e+00AX^P-WW+L=R@2_2/A:2/B:3-2-&14-20|WW/C:2/D:2/E:3+&7/F:4/H:12=33.state[5]: duration=1 (frame), mean=3.948951e+00AX^P-WW+L=R@2_2/A:2/B:3-2-&14-20|WW/C:2/D:2/E:3+&7/F:4/H:12=33.state[6]: duration=1 (frame), mean=3.052463e+00AX^P-WW+L=R@2_2/A:2/B:3-2-&14-20|WW/C:2/D:2/E:3+&7/F:4/H:12=33: duration=5 (frame), mean=1.385496e+01 Duration model~s "dur_s2_1623" 1 1 1.306419e+00 1 1.695042e-01 6.299961e-02 2 1 2.176778e+00 1 1.851734e+00 2.454000e+00 3 1 3.774895e+00 1 1.702917e+01 4.672805e+00 4 1 5.540838e+00 1 3.468322e+01 5.384133e+00 5 1 2.440767e+00 1 8.953208e+00 4.029889e+00

Follow-Ups
[hts-users:03240] Re: duration modeling and dur file, Keiichiro Oura