[hts-users:00324] Re: some questions about hts_engine and HTS_demo
- Subject: [hts-users:00324] Re: some questions about hts_engine and HTS_demo
- From: "lei liu" <wenshiliu@xxxxxxxxx>
- Date: Thu, 25 May 2006 16:57:26 +0800
- Domainkey-signature: a=rsa-sha1; q=dns; c=nofws; s=beta; d=gmail.com; h=received:message-id:date:from:to:subject:in-reply-to:mime-version:content-type:references; b=DPMnED4IyFblf5QzB93gzeT4DzWPUPVIjX1s8SpA8oRA50PwccgrI3t6126dDYr2n+bPa/dXs4zqjZ2CRiZ0EVkEggGjZH4x70npwsTKsaBYOJjngDUacb03o0yp11OhJ3Cok1Zmgpoj8p/zQoDNhbS0A4/D9bH842DHkwATYLA=
hi
sorry ,
it is my mistake,
I did not see the ex. 75
Best regards
2006/5/25, Heiga ZEN (Byung Ha CHUN) <zen@xxxxxxxxxxxxxxxx>:
Hi
lei liu wrote:
> thank you
> I will check my pdf file.
>
> In the mcp.pdf
,
> it is defined 75 dimension for the mean vector of leaf node,
> as this
> "4byte float, 75th dim. of mean vector at last leaf node"
Dimensionality depends on MCEPORDER and number of dynamic features.
In our demo, 24-order mel-cepstral coefficients including the zero-th coefficients, delta and delta-delta are used.
So dimensionality of feature vector becomes 75.
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://kt-lab.ics.nitech.ac.jp/~zen
------------------------------------------------
- References
-
- [hts-users:00318] some questions about hts_engine and HTS_demo, lei liu
- [hts-users:00319] Re: some questions about hts_engine and HTS_demo, Heiga ZEN (Byung Ha CHUN)
- [hts-users:00320] Re: some questions about hts_engine and HTS_demo, lei liu
- [hts-users:00321] Re: some questions about hts_engine and HTS_demo, Heiga ZEN (Byung Ha CHUN)
- [hts-users:00322] Re: some questions about hts_engine and HTS_demo, lei liu
- [hts-users:00323] Re: some questions about hts_engine and HTS_demo, Heiga ZEN (Byung Ha CHUN)