1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
|
/*
* Average Magnitude Difference Function (AMDF) voicing detector for speech analysis
* Copyright (c) 2005, Dr Edward Kelly <morph_2016@yahoo.co.uk>
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without modification,
* are permitted provided that the following conditions are met:
*
* Redistributions of source code must retain the above copyright notice,
* this list of conditions and the following disclaimer.
*
* Redistributions in binary form must reproduce the above copyright notice, this list
* of conditions and the following disclaimer in the documentation and/or other materials
*
* provided with the distribution.
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND ANY
* EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
* OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT
* SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
* PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
* INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/
#include "m_pd.h"
#include <math.h>
static t_class *voicing_detector_tilde_class;
typedef struct _voicing_control
{
t_float *c_input;
t_float f_sum_abs;
t_atom otemp[4096];
t_int method;
} t_voicing_control;
typedef struct _voicing_detector_tilde
{
t_object x_obj;
t_float f_dummy, f_thresh, f_low, f_high;
t_voicing_control x_ctl;
t_outlet *voiced, *prob;
} t_voicing_detector_tilde;
static t_int *voicing_detector_tilde_perform(t_int *w)
{
t_voicing_detector_tilde *x = (t_voicing_detector_tilde *)(w[1]);
t_voicing_control *ctl = (t_voicing_control *)(w[2]);
t_int n = (int)(w[3]);
t_float *in = ctl->c_input;
if (x->f_high < x->f_low)
{
float tmp = x->f_low;
x->f_low = x->f_high;
x->f_high = tmp;
}
t_float current, previous, next, temp0, temp1, avg, max, peak0;
current = previous = next = temp0 = temp1 = avg = max = peak0 = 0;
t_float min = 1000;
t_float samplerate = sys_getsr();
t_float start = samplerate / x->f_high;
start = start > 1 ? start : 1;
t_float end = samplerate / x->f_low;
end = end < (n-1) ? end : n-1;
t_float result, prob, diff, diff2;
t_int i = 0;
int j;
int l = n;
int maxp = 0;
int maxi = 0;
float temp[n];
ctl->f_sum_abs = 0.0;
for (i=0;i<l;i++)
{
ctl->f_sum_abs += fabs(in[i]); /* I have to calculate f_sum_abs for the whole block before I can calculate amdf */
temp[i] = 0.0;
SETFLOAT(&ctl->otemp[i], 0.0);
}
for (i=1;i<l;i++)
{
temp1 = 0;
for (j=start;j<=end;j++) /* the Average Magnitude Difference Function */
{
temp[j] = i + j < l ? in[i+j] : 0.0;
temp0 = atom_getfloatarg(i, 4096, ctl->otemp);
temp1 += fabs(in[j] - temp[j]);
}
temp1 += ((float)i / (float)l) * ctl->f_sum_abs;
SETFLOAT(&ctl->otemp[i], temp1);
}
for (i=start+1;i<end;i++)
{
previous= atom_getfloatarg(i-1, 2048, ctl->otemp);
current = atom_getfloatarg(i, 2048, ctl->otemp);
next = atom_getfloatarg(i+1, 2048, ctl->otemp);
max = current > max ? current : max;
min = current < min ? current : min;
avg += current;
}
avg = avg / (end-start);
diff = avg - min;
diff2 = max - min;
result = ctl->method == 0 ? ((avg - min) > (x->f_thresh) ? 1 : 0) : ((max - min) > x->f_thresh ? 1 : 0);
prob = diff2 / max;
outlet_float(x->prob, prob);
outlet_float(x->voiced, result);
return(w+4);
}
void voicing_detector_tilde_bound(t_voicing_detector_tilde *x, t_floatarg f1, t_floatarg f2)
{
x->f_low = f1;
x->f_high = f2;
}
void voicing_detector_tilde_method(t_voicing_detector_tilde *x, t_floatarg f)
{
x->x_ctl.method = f > 0 ? 1 : 0;
}
void *voicing_detector_tilde_dsp(t_voicing_detector_tilde *x, t_signal **sp)
{
x->x_ctl.c_input = sp[0]->s_vec;
dsp_add(voicing_detector_tilde_perform, 3, x, &x->x_ctl, sp[0]->s_n);
return (void *)x;
}
void *voicing_detector_tilde_new(t_floatarg f)
{
t_voicing_detector_tilde *x = (t_voicing_detector_tilde *)pd_new(voicing_detector_tilde_class);
x->f_thresh = f < 0 ? f : 25;
x->f_low = 60;
x->f_high = 500;
floatinlet_new (&x->x_obj, &x->f_thresh);
x->voiced = outlet_new(&x->x_obj, gensym("float"));
x->prob = outlet_new(&x->x_obj, gensym("float"));
return (void *)x;
}
void voicing_detector_tilde_setup(void)
{
voicing_detector_tilde_class = class_new(gensym("voicing_detector~"), (t_newmethod)voicing_detector_tilde_new, 0, sizeof(t_voicing_detector_tilde), CLASS_DEFAULT, A_DEFFLOAT, 0);
post("\n-->AMDF voicing detector v0.2");
post("-->by Nicolas Chetry <okin@altern.org>");
post("-->& Edward Kelly <morph_2016@yahoo.co.uk>");
class_addmethod(voicing_detector_tilde_class, (t_method)voicing_detector_tilde_bound, gensym("bound"), A_DEFFLOAT, A_DEFFLOAT, 0);
class_addmethod(voicing_detector_tilde_class, (t_method)voicing_detector_tilde_method, gensym("method"), A_DEFFLOAT, 0);
class_addmethod(voicing_detector_tilde_class, (t_method)voicing_detector_tilde_dsp, gensym("dsp"), 0);
CLASS_MAINSIGNALIN(voicing_detector_tilde_class, t_voicing_detector_tilde, f_dummy);
}
|
