mirror of
https://github.com/rhasspy/espeak-ng.git
synced 2026-10-31 05:35:35 +00:00
jonsd
1150d1d8da
Added experimental Klatt synthesizer. Klatt phonemes use a new format of phoneme data. espeakedit, new dialog fields and layout for Klatt phonemes. Added Klatt versions of English phonemes. Fixed some compilation warnings on Windows. Fixed bug in Lettergroups > L10 Increased amplitude of harmonics below F1 peak, to increase bass. Allow 5 (up from 4) pairs of values in "tone" command in voice files. Default to slightly wider pk_shape1. If words are separated by hyphens, don't add word-gap, and don't pass new-word flag onto phoneme processing. git-svn-id: https://espeak.svn.sourceforge.net/svnroot/espeak/trunk@203 d46cf337-b52f-0410-862d-fd96e6ae7743
82 lines
3.4 KiB
C
82 lines
3.4 KiB
C
/***************************************************************************
|
|
* Copyright (C) 2005 to 2007 by Jonathan Duddington *
|
|
* email: jonsd@users.sourceforge.net *
|
|
* *
|
|
* This program is free software; you can redistribute it and/or modify *
|
|
* it under the terms of the GNU General Public License as published by *
|
|
* the Free Software Foundation; either version 3 of the License, or *
|
|
* (at your option) any later version. *
|
|
* *
|
|
* This program is distributed in the hope that it will be useful, *
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of *
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the *
|
|
* GNU General Public License for more details. *
|
|
* *
|
|
* You should have received a copy of the GNU General Public License *
|
|
* along with this program; if not, write see: *
|
|
* <http://www.gnu.org/licenses/>. *
|
|
***************************************************************************/
|
|
|
|
|
|
|
|
typedef struct {
|
|
char v_name[40];
|
|
|
|
int phoneme_tab_ix; // phoneme table number
|
|
int pitch_base; // Hz<<12
|
|
int pitch_range; // standard = 0x1000
|
|
|
|
int speedf1;
|
|
int speedf2;
|
|
int speedf3;
|
|
|
|
int flutter;
|
|
int roughness;
|
|
int echo_delay;
|
|
int echo_amp;
|
|
int n_harmonic_peaks; // highest formant which is formed from adding harmonics
|
|
int peak_shape; // alternative shape for formant peaks (0=standard 1=squarer)
|
|
int voicing; // 100% = 64, level of formant-synthesized sound
|
|
int formant_factor; // adjust nominal formant frequencies by this because of the voice's pitch (256ths)
|
|
int consonant_amp; // amplitude of unvoiced consonants
|
|
int consonant_ampv; // amplitude of the noise component of voiced consonants
|
|
int klatt[8];
|
|
|
|
// parameters used by Wavegen
|
|
short freq[N_PEAKS]; // 100% = 256
|
|
short height[N_PEAKS]; // 100% = 256
|
|
short width[N_PEAKS]; // 100% = 256
|
|
short freqadd[N_PEAKS]; // Hz
|
|
|
|
// copies without temporary adjustments from embedded commands
|
|
short freq2[N_PEAKS]; // 100% = 256
|
|
short height2[N_PEAKS]; // 100% = 256
|
|
short width2[N_PEAKS]; // 100% = 256
|
|
|
|
int breath[N_PEAKS]; // amount of breath for each formant. breath[0] indicates whether any are set.
|
|
int breathw[N_PEAKS]; // width of each breath formant
|
|
|
|
// This table provides the opportunity for tone control.
|
|
// Adjustment of harmonic amplitudes, steps of 8Hz
|
|
// value of 128 means no change
|
|
#define N_TONE_ADJUST 1000
|
|
unsigned char tone_adjust[N_TONE_ADJUST]; // 8Hz steps * 1000 = 8kHz
|
|
|
|
} voice_t;
|
|
|
|
// percentages shown to user, ix=N_PEAKS means ALL peaks
|
|
extern USHORT voice_pcnt[N_PEAKS+1][3];
|
|
|
|
|
|
extern voice_t *voice;
|
|
extern int tone_points[12];
|
|
|
|
const char *SelectVoice(espeak_VOICE *voice_select);
|
|
espeak_VOICE *SelectVoiceByName(espeak_VOICE **voices, const char *name);
|
|
voice_t *LoadVoice(const char *voice_name, int control);
|
|
voice_t *LoadVoiceVariant(const char *voice_name, int variant);
|
|
void DoVoiceChange(voice_t *v);
|
|
void WavegenSetVoice(voice_t *v);
|
|
void ReadTonePoints(char *string, int *tone_pts);
|
|
|