.TH "htsengine" "1" .SH "NAME" hts_engine \(em HMM-based speech synthesis engine .SH "SYNOPSIS" .PP \fBhts_engine\fR [\fBoptions\fP] [\fBinfile\fP] .SH "DESCRIPTION" .PP This manual page documents briefly the \fBhts_engine\fR command. .PP This manual page was written for the \fBDebian\fP distribution because the original program does not have a manual page. Instead, it has documentation in the GNU \fBInfo\fP format; see below. .PP \fBhts_engine\fR is a program that synthesize speech waveform from HMMs trained by the HMM-based speech synthesis system (HTS). .SH "OPTIONS" .PP A summary of options is included below. .IP "\fB-m htsvoice\fP" 10 HTS voice files .IP "\fB-od s\fP" 10 filename of output label with duration .IP "\fB-om s\fP" 10 filename of output spectrum .IP "\fB-of s\fP" 10 filename of output Log F0 .IP "\fB-ol s\fP" 10 filename of output low-pass filter .IP "\fB-or s\fP" 10 filename of output raw audio (generated speech) .IP "\fB-ow s\fP" 10 filename of output wav audio (generated speech) .IP "\fB-ot s\fP" 10 filename of output trace information .IP "\fB-vp\fP" 10 use phoneme alignment for duration .IP "\fB-i i f1 .. fi\fP" 10 enable interpolation & specify number(i),coefficient(f) .IP "\fB-s i\fP" 10 sampling frequency [auto][ 1\-\- ] .IP "\fB-p i\fP" 10 frame period (point) [auto][ 1\-\- ] .IP "\fB-a f\fP" 10 all-pass constant [auto][0.0\-\-1.0] .IP "\fB-b f\fP" 10 postfiltering coefficient [0.0][0.0\-\-1.0] .IP "\fB-r f\fP" 10 speech speed rate [1.0][0.0\-\- ] .IP "\fB-fm f\fP" 10 add half-tone [0.0][ \-\- ] .IP "\fB-u f\fP" 10 voiced/unvoiced threshold[0.5][0.0\-\-1.0] .IP "\fB-jm f\fP" 10 weight of GV for spectrum [1.0][0.0\-\- ] .IP "\fB-jf f\fP" 10 weight of GV for Log F0 [1.0][0.0\-\- ] .IP "\fB-z i\fP" 10 audio buffer size (if i==0, turn off) [ 0][0\-\- ] .IP "\fBinfile\fP" 10 label file .PP generated spectrum, log F0, and low-pass filter coefficient sequences are saved in natural endian, binary (float) format. .SH "EXAMPLE" .PP 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: .PP .RS .PP .nf % hts_engine \-s 48000 \-p 240 \-a 0.55 \\ \-m nitech_jp_atr503_m001.htsvoice \\ \-ow output.wav \\ input.lab .fi .PP .RE .SH "AUTHOR" .PP This manual page was written by Koichi Akabe vbkaisetsu@gmail.com for the \fBDebian\fP 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. .PP On Debian systems, the complete text of the GNU General Public License can be found in /usr/share/common-licenses/GPL. .\" created by instant / docbook-to-man