
Installation of HTS-demo_Nitech-ATR503-M001
==========================================

1. HTS-demo_Nitech-ATR503-M001 requires SPTK and HTS.
   Please install them before trying this demo.
   You can download them from
   
   SPTK: http://kt-lab.ics.nitech.ac.jp/~tokuda/SPTK/
   HTS: http://hts.ics.nitech.ac.jp/
   
   In HTS-demo_Nitech-ATR503-M001, an F0 extraction script written in Tcl/Tk is included. 
   This script calls a function implemented on the open-source speech toolkit *Snack*.	
   Therefore, HTS-demo_Nitech-ATR503-M001 also requires Tcl/Tk with Snack on your environment.
   ActiveState (http://www.activestate.com/) provides a Tcl/Tk distribution named ActiveTcl
   for many platforms. You can download it from 

   ActiveTcl: http://www.activestate.com/Products/ActiveTcl/

   This distribution includes Snack and it is easy to install and use.
   I recommend you to use this for running the demonstration
   (Of course you can use your own tcl/tk with Snack).
   
      
2. Setup HTS-demo_Nitech-ATR503-M001 by running configure script:

   % cd HTS-demo_Nitech-ATR503-M001
   % ./configure --with-tcl-search-path=/usr/local/ActiveTcl/bin \
                 --with-sptk-search-path=/usr/local/SPTK/bin \
                 --with-hts-search-path=/usr/local/HTS-2.0_for_HTK-3.4/bin	

   Please adjust the above directories for your environment.
   Note that you should specify festival/examples rather than festival/bin.

   You can change speech analysis conditions such as order of mel-cepstral analysis 
   through ./configure arguments:

   % ./configure MCPORDER=24

   For detail, please refer 

   % ./configure --help


3. Start running demonstration as follows:

   % cd HTS-demo_Nitech-ATR503-M001
   % make

   After composing training data, HMMs are estimated and speech waveforms are synthesized.
   It takes about 6 to 12 hours :-) 

