HMGenS's -m option should definitely work; the HTS-demo_NIT-SONG070-F001 demo even uses it..
Do your `gen` .lab files contain valid begin/end times?
What happens? Do you get some error?
The -m option allows you to fix model (phoneme) durations, however relative state durations are still determined by the duration model (so -N is needed).
Merlijn
Thursday, December 17, 2015 16:16 via PostboxDear esteemed gentlemen,Thank you very much.Unfortunately, -m option doesn't work for me.I also used -m option without duration model (-N option), it causes problem of missing files (ERROR 7010: Load HMMSet)I don't know why HTS uses different ways to generate parameters and synthesized voices (HMGenS and hts_engine).I will find another way to synthesized speech with pre-defined durations of phonemes using HMGenS.Best regards-TuanThursday, December 3, 2015 15:43 via PostboxHello
I think you are looking for the -m option.
Kind regards
Sébastien Le MaguerEnvoyé avec AquaMail pour Android
http://www.aqua-mail.comLe 3 décembre 2015 15:42:26 Tuan Dinh <tuan.dinh@xxxxxxxxx> a écrit :
Thursday, December 3, 2015 15:42 via PostboxThanks you very much. I very appreciate.But I expect something like "-vp" option of hts_engine.Isn't any similar option with HMMGenS to use pre-specified duration of phonemes.Best regards.-TuanThursday, December 3, 2015 14:29 via PostboxHello,This post may help you http://www.nguyenquyhy.com/2013/12/how-to-configure-hts-for-in-training-synthesis-with-state-level-alignment-labels//BajiThursday, December 3, 2015 14:03 via PostboxHi all,I have label files with duration information. How can I make HMGenS use the duration information in synthesizing speech? Thank you very much.Best regards,-Tuan