[hts-users:01473] Re: Trying new language on HTS

["Anocha Rugchatjaroen" <anocha.rugchatjaroen@xxxxxxxxxxxx>]

Sorry, I forgot to tell you about our sampling rate. We record the speech
in 44k sampling rate and resampling to 16k and train to the system.

Thank you for adv.
Best regards,

Anocha


> I'm curious about the sample rate. Is 8000 the native sample rate of
> your speech data? Try -s 16000.
>
> br,
>   Nicholas
>
>>
>>> Hi,
>>>
>>> Anocha Rugchatjaroen wrote (2008/06/25 16:19):
>>>
>>>> We are trying Dzongkha language on HTS. What we have done is
>>>> training a set of speech using HTS-demo_CMU_ARCTIC_SLT as a template
>>>> without using DUMPFEATS of festival and setting up a training set as
>>>> :
>>>> 	- 53 phonemes ( consonants,  vowels) with 2 tones
>>>> 	- 509 sentences (cover all diphone)
>>>> 	- and automatic labeling using htk flat start.
>>>> After we trained the script, we found that if we use full format of
>>>> label file for generating speech - like
>>>>
>>>> 0       11900001 q_q-$+m=i/A:0
>>>> 11900000        13300000 q_$-m+i=ph/A:0
>>>> 13300000        15100000 $_m-i+ph=e/A:0
>>>> 15100000        16100000 m_i-ph+e=l/A:0
>>>> 16100000        17000000 i_ph-e+l=ph/A:0
>>>> ...
>>>>
>>>> we can get a good synthesized speech. But if we use only
>>>>
>>>> q_q-$+m=i/A:0
>>>> q_$-m+i=ph/A:0
>>>> $_m-i+ph=e/A:0
>>>> m_i-ph+e=l/A:0
>>>> i_ph-e+l=ph/A:0
>>>> ...
>>>>
>>>> we got very small speech - like a half of a syllable.
>>>>
>>>> Did we do anything wrong? Is our number of sentences too small?
>>>> Could you please suggest us?
>>>
>>> Did you use hts_engine or HMGenS?
>>> Can you show us the command line arguments to generate speech
>>> parameters?
>>
>> we use hts_engine as this command.
>>
>> hts_engine -td tree-dur.inf -tf tree-lf0.inf -tm tree-mcp.inf -md
>> dur.pdf -mf lf0.pdf -mm mcp.pdf -dm mcp.win1 -dm mcp.w
>> in2 -dm mcp.win3 -df lf0.win1 -df lf0.win2 -df lf0.win3 -or tmp.raw
>> tmp.lab  -s 8000 -p 40 -a 0.42 -b 0.4
>>
>> Best regards,
>>
>> Anocha
>>
>>>
>>> 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
>>> ------------------------------------------------
>>
>>
>>
>> Human Language Technology (HLT) Lab
>> National Electronics and Computer Technology Center (NECTEC)
>> 112 Phahonyothin Rd., Klong 1, Klong Luang,
>> Pathumthani 12120
>> THAILAND
>>
>> Tel.  (+66) 2 564-6900 Ext. 2231
>> Fax. (+66) 2 564-6873



Human Language Technology (HLT) Lab
National Electronics and Computer Technology Center (NECTEC)
112 Phahonyothin Rd., Klong 1, Klong Luang,
Pathumthani 12120
THAILAND

Tel.  (+66) 2 564-6900 Ext. 2231
Fax. (+66) 2 564-6873