[hts-users:00006] Re: HTS Query
Dear Terry Martin,
From: "Terry Martin" <tl.martin@xxxxxxxxxx>
Subject: HTS Query
Date: Wed, 21 Jan 2004 11:59:56 +1000
Message-ID: <012101c3dfc2$44d14240$b611b583@xxxxxxxxxxxxxxx>
> Dear Sir,
>
> I was extremely pleased to see that you work incorporates a
> number of tools which prove to be useful for speech science
> and thankyou for your efforts. Of most interest was a comment
> on HTK web page which stated that the latest version of HTS
> can do Context clustering based on MDL criterion (instead of
> ML one) . However I have been able to find any reference to
> this in your English drafted reference guide. If you could
> possibly direct me to papers you have published and some
> command line examples for using this I would be most grateful.
>
> Cheers
> Terry Martin PhD student
> Queensland University of Technology
> Australia
The following references would be helpful.
Takayoshi Yoshimura, Keiichi Tokuda, Takashi Masuko, Takao
Kobayashi and Tadashi Kitamura, ``Simultaneous modeling of
spectrum, pitch and duration in HMM-based speech synthesis,''
Proceedings of European Conference on Speech Communication and
Technology, Budapest, Hungary, vol.5, pp.2347-2350, Sep. 1999.
K. Shinoda and T. Watanabe, ``MDL-based context-dependent
subword modeling for speech recognition,''
J. Acoust. Soc. Jpn.(E), vol. 21, no. 2, pp.79-86, 2000.
K. Shinoda and T. Watanabe, ``Acoustic modeling based on the
MDL criterion for speech recognition,'' in
Proc. EuroSpeech-97, Rhodes, vol. 1, pp. 99-102, 1997.
Other inquiries could be sent to "hts-users" mailing list. See
http://hts.ics.nitech.ac.jp/mailinglists.html
Best regards,
Keiichi Tokuda
tokuda@xxxxxxxxxxxxxxxx
http://kt-lab.ics.nitech.ac.jp/~tokuda/