Dear Heiga
i encountered this error when i was recording the trainning data.i recorded the training data many times for each sentences till it worked . i don't know yet why this error happen also when i used the same sentences without dynamic features
so plz let me know if i will use the HMM trained with dynamic features to synthesis speech without the dynamic features
i mean how to synthesis voice without the usage od dynamic features
what steps to follow to make this ?
Thanks Alot
Tamer Fares
From: "Heiga ZEN (Byung Ha CHUN)" <zen@xxxxxxxxxxxxxxx>
Reply-To: hts-users@xxxxxxxxxxxxxxx
To: hts-users@xxxxxxxxxxxxxxx
Subject: [hts-users:00802] Re: Static And Dynamic Features
Date: Sun, 23 Sep 2007 20:23:40 +0900
>Hi,
>
>Tamer Fares wrote (2007/09/23 20:13):
>
>>i did what u said
>>
>>i generate the proto with only 2 streams
>>
>>but when finished the computation of the global variance and the
>>starting of the monophone mmf , its starts the start embeded
>>reestimation of monophone and give me the following error
>>
>>processing data : tamer001.cmp ; label tamer001.lab
>>
>>retrying beta pass at 1100.0
>>.
>>.
>>.
>>retrying beta pass at 3200.0
>>
>>all sentences was working with the dynamic features
>>
>>what should i do?
>
>I did this in the same way and worked correctly.
>So it may be your bug, please check your data and script.
>
>Regards,
>
>Heiga ZEN (Byung Ha CHUN)
>
>--
>------------------------------------------------
>Heiga ZEN (in Japanese pronunciation)
>Byung Ha CHUN (in Korean pronunciation)
>
>Department of Computer Science and Engineering
>Nagoya Institute of Technology
>Gokiso-cho, Showa-ku, Nagoya 466-8555 Japan
>
>http://www.sp.nitech.ac.jp/~zen
>------------------------------------------------
>