[hts-users:03505] Re: The synthesized waveform of HTS2.2(Straight) using LSP is silence
- Subject: [hts-users:03505] Re: The synthesized waveform of HTS2.2(Straight) using LSP is silence
- From: Keiichiro Oura <uratec@xxxxxxxxxxxxxxx>
- Date: Fri, 30 Nov 2012 01:27:51 +0900
- Cc: uratec <uratec@xxxxxxxxxxxx>
- Delivered-to: hts-users@xxxxxxxxxxxxxxx
- Dkim-signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:sender:in-reply-to:references:date :x-google-sender-auth:message-id:subject:from:to:cc:content-type :content-transfer-encoding; bh=0h8YyhbhxdQ4mPHeWTympClPLebBIP+FkrJaxM/Zp+8=; b=SVbXIEn+gBbE0BlIMXg9Vsi52pU+/97vHvYYMHTq9HzKrCHecY9tWUxDWqH4gKYmTB 5e0zWkV9toC43GAQBhx8P+4opF7v0Ex87xzYL5FiG7oL/cBlKXb9a2aCsUzxb1ww9Vhs VJ7o2P6rBut35yrF4oJf0PFSSgUtROA0cqCtSmE3tkiqLzSBKGxjUiAvx88BmXoHLxWd qavl7gux2wv/7ObIzkho9ykXkOswAPIHf7ECOQu5fImAPfg7PIPa+xTisKOB99XXKCkx t+4BEVrE3HwlvRtlZ3Ltu88t7VPw3V+iFSat1wKYCO2gF9HMSbR22OFXk/ToxnmjsvQZ dGCQ==
Hi,
Although I recommend that you use CVS, the latest source code of SPTK
can be found in following URL.
http://sp-tk.cvs.sourceforge.net/viewvc/sp-tk/SPTK/src/
Regards,
Keiichiro Oura
2012/11/29 ArthurLeo <bin007.zhao@xxxxxxxxxxx>:
> I tried to access the sptk cvs server, but failed, Could you tell me the
> fixed bug of mgc2mgc in the latest
> SPTK?
>
> Thank you very much!
>
>> Date: Wed, 28 Nov 2012 00:55:58 +0900
>> From: uratec@xxxxxxxxxxxxxxx
>> Subject: [hts-users:03497] Re: The synthesized waveform of
>> HTS2.2(Straight) using LSP is silence
>> To: hts-users@xxxxxxxxxxxxxxx
>> CC: uratec@xxxxxxxxxxxx
>
>>
>> Hi,
>>
>> This is the information about SPTK CVS server.
>> http://sourceforge.net/scm/?type=cvs&group_id=176586
>>
>> Regards,
>> Keiichiro Oura
>>
>>
>> 2012/11/28 ArthurLeo <bin007.zhao@xxxxxxxxxxx>:
>> > Can you supply with latest sptk?or give me some information about the
>> > address of cvs?
>> >
>> > Keiichiro Oura <uratec@xxxxxxxxxxxxxxx>编写:
>> >
>> > Hi,
>> >
>> > Could you try to use latest SPTK in sourceforge CVS server ?
>> > There is a bug in mgc2mgc of SPTK-3.5.
>> >
>> > Regards,
>> > Keiichiro Oura
>> >
>> >
>> > 2012/11/28 ArthurLeo <bin007.zhao@xxxxxxxxxxx>:
>> >> I also encounterd this problem. I checked the lsp predicted by the
>> >> model,
>> >> found that most of LSPs 's order and the consecutive distance are
>> >> normal.
>> >> but when I checked the parameters after mgc2sp proceessed, It became
>> >> abnormal, a lot of the sp are very large, such as 8.2334e+35, so I
>> >> guess it
>> >> must
>> >> be something wrong.
>> >>
>> >> then I checked the parameters after LSP2LPC and MGC2MGC proceessed. The
>> >> parameters after LSP2LPC seem to be normal, but the parameters after
>> >> MGC2MGC maybe something wrong. Because the lpc parameters became very
>> >> large,
>> >> such as 984.623.
>> >>
>> >> What is the most likely problem for LSP2LPC and mgc2mgc in general?
>> >> especially the lsps seem to be
>> >> normal?
>> >>
>> >>> Date: Wed, 21 Nov 2012 17:14:25 +0900
>> >>> From: heigazen@xxxxxxxxxx
>> >>> Subject: [hts-users:03469] Re: The synthesized waveform of
>> >>> HTS2.2(Straight) using LSP is silence
>> >>> To: hts-users@xxxxxxxxxxxxxxx
>> >>>
>> >>> I expect
>> >>>
>> >>> 1. some generated LSPs became unstable
>> >>> 2. the MATLAB STRAIGHT code synthesized speech waveform in float,
>> >>> which became very large as filters were unstable
>> >>> 3. the MATLAB STRAIGHT code scaled the amplitude of speech waveform
>> >>> according to the maximum value while saving wav in short
>> >>> 4. as the maximum value was very large, almost all points in the wav
>> >>> file became 0
>> >>>
>> >>> Please check the generated LSPs are stable or not. You can convert
>> >>> LSP into spectrum and plot it using SPTK. Please refer to the SPTK
>> >>> manual.
>> >>>
>> >>> Regards,
>> >>>
>> >>> Heiga
>> >>>
>> >>>
>> >>>
>> >>> 2012/11/21 北语语音组成员李伟 <blculiwei@xxxxxxxxx>:
>> >>> > Hi, actually the matlab and straight are fine, because if they
>> >>> > doesn't
>> >>> > work,
>> >>> > I can't achieve synthesized wave using default settings.
>> >>> > BTW: I had checked the BAP file, it's not empty.
>> >>> > Thanks
>> >>> >
>> >>> > 2012/11/21 Thanh-Son PHAN <sonphan.hts@xxxxxxxxx>
>> >>> >>
>> >>> >> HT did not run, see B
>> >>> >
>> >>> >
>> >>> >
>> >>> >
>> >>> > --
>> >>> >
>> >>> > Li wei
>> >>> > Department of Information Science, Beijing Language and Culture
>> >>> > University
>> >>> > Room 208a, Bulding 15, Beijing Language and Culture University,
>> >>> > Haidian
>> >>> > District, Beijing,P. R. China
>> >>> > Post code:100083
>> >>> > Mobile: 15110081848
>> >>> > E-mail: blculiwei@xxxxxxxxx
>> >>> >
>> >>>
>> >>>
>> >>>
>> >>> --
>> >>> Heiga ZEN (in Japanese)
>> >>> Byung Ha CHUN (in Korean)
>> >>> <heigazen@xxxxxxxxxx>
>> >>>
>> >
>> >
>>
- References
-
- [hts-users:03496] Re: The synthesized waveform of HTS2.2(Straight) using LSP is silence, ArthurLeo
- [hts-users:03497] Re: The synthesized waveform of HTS2.2(Straight) using LSP is silence, Keiichiro Oura
- [hts-users:03504] Re: The synthesized waveform of HTS2.2(Straight) using LSP is silence, ArthurLeo