Hts_engine hmm-based speech synthesis engine
hts_engine [options] [infile]
This manual page documents briefly the hts_engine command.
This manual page was written for the Debian distribution because the original program does not have a manual page. Instead, it has documentation in the GNU Info format; see below.
hts_engine is a program that synthesize speech waveform from HMMs trained by the HMM-based speech synthesis system (HTS).
A summary of options is included below.
HTS voice files
filename of output label with duration
filename of output spectrum
filename of output Log F0
filename of output low-pass filter
filename of output raw audio (generated speech)
filename of output wav audio (generated speech)
filename of output trace information
use phoneme alignment for duration
enable interpolation & specify number(i),coefficient(f)
sampling frequency [auto][ 1-- ]
frame period (point) [auto][ 1-- ]
all-pass constant [auto][0.0--1.0]
postfiltering coefficient [0.0][0.0--1.0]
speech speed rate [1.0][0.0-- ]
add half-tone [0.0][ -- ]
voiced/unvoiced threshold[0.5][0.0--1.0]
weight of GV for spectrum [1.0][0.0-- ]
weight of GV for Log F0 [1.0][0.0-- ]
audio buffer size (if i==0, turn off) [ 0][0-- ]
label file
generated spectrum, log F0, and low-pass filter coefficient sequences are saved in natural endian, binary (float) format.
If you installed hts-voice-nitech-jp-atr503-m001 in the current directory, the following command let you make a voice file from input.lab:
% hts_engine -s 48000 -p 240 -a 0.55 \ -m nitech_jp_atr503_m001.htsvoice \ -ow output.wav \ input.lab
This manual page was written by Koichi Akabe [email protected] for the Debian system (and may be used by others). Permission is granted to copy, distribute and/or modify this document under the terms of the GNU General Public License, Version 2 any later version published by the Free Software Foundation.
On Debian systems, the complete text of the GNU General Public License can be found in /usr/share/common-licenses/GPL.