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
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363 | /**************************************************************************/
/* audio_effect_pitch_shift.cpp */
/**************************************************************************/
/* This file is part of: */
/* GODOT ENGINE */
/* https://godotengine.org */
/**************************************************************************/
/* Copyright (c) 2014-present Godot Engine contributors (see AUTHORS.md). */
/* Copyright (c) 2007-2014 Juan Linietsky, Ariel Manzur. */
/* */
/* Permission is hereby granted, free of charge, to any person obtaining */
/* a copy of this software and associated documentation files (the */
/* "Software"), to deal in the Software without restriction, including */
/* without limitation the rights to use, copy, modify, merge, publish, */
/* distribute, sublicense, and/or sell copies of the Software, and to */
/* permit persons to whom the Software is furnished to do so, subject to */
/* the following conditions: */
/* */
/* The above copyright notice and this permission notice shall be */
/* included in all copies or substantial portions of the Software. */
/* */
/* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, */
/* EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF */
/* MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. */
/* IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY */
/* CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, */
/* TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE */
/* SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. */
/**************************************************************************/
#include "audio_effect_pitch_shift.h"
#include "core/math/math_funcs.h"
#include "servers/audio_server.h"
/* Thirdparty code, so disable clang-format with Godot style */
/* clang-format off */
/****************************************************************************
*
* NAME: smbPitchShift.cpp
* VERSION: 1.2
* HOME URL: https://blogs.zynaptiq.com/bernsee
* KNOWN BUGS: none
*
* SYNOPSIS: Routine for doing pitch shifting while maintaining
* duration using the Short Time Fourier Transform.
*
* DESCRIPTION: The routine takes a pitchShift factor value which is between 0.5
* (one octave down) and 2. (one octave up). A value of exactly 1 does not change
* the pitch. numSampsToProcess tells the routine how many samples in indata[0...
* numSampsToProcess-1] should be pitch shifted and moved to outdata[0 ...
* numSampsToProcess-1]. The two buffers can be identical (ie. it can process the
* data in-place). fftFrameSize defines the FFT frame size used for the
* processing. Typical values are 1024, 2048 and 4096. It may be any value <=
* MAX_FRAME_LENGTH but it MUST be a power of 2. osamp is the STFT
* oversampling factor which also determines the overlap between adjacent STFT
* frames. It should at least be 4 for moderate scaling ratios. A value of 32 is
* recommended for best quality. sampleRate takes the sample rate for the signal
* in unit Hz, ie. 44100 for 44.1 kHz audio. The data passed to the routine in
* indata[] should be in the range [-1.0, 1.0), which is also the output range
* for the data, make sure you scale the data accordingly (for 16bit signed integers
* you would have to divide (and multiply) by 32768).
*
* COPYRIGHT 1999-2015 Stephan M. Bernsee <s.bernsee [AT] zynaptiq [DOT] com>
*
* The Wide Open License (WOL)
*
* Permission to use, copy, modify, distribute and sell this software and its
* documentation for any purpose is hereby granted without fee, provided that
* the above copyright notice and this license appear in all source copies.
* THIS SOFTWARE IS PROVIDED "AS IS" WITHOUT EXPRESS OR IMPLIED WARRANTY OF
* ANY KIND. See https://dspguru.com/wide-open-license/ for more information.
*
*****************************************************************************/
void SMBPitchShift::PitchShift(float pitchShift, long numSampsToProcess, long fftFrameSize, long osamp, float sampleRate, float *indata, float *outdata,int stride) {<--- Parameter 'indata' can be declared with const
/*
Routine smbPitchShift(). See top of file for explanation
Purpose: doing pitch shifting while maintaining duration using the Short
Time Fourier Transform.
Author: (c)1999-2015 Stephan M. Bernsee <s.bernsee [AT] zynaptiq [DOT] com>
*/
double magn, phase, tmp, window, real, imag;
double freqPerBin, expct;
long i,k, qpd, index, inFifoLatency, stepSize, fftFrameSize2;
/* set up some handy variables */
fftFrameSize2 = fftFrameSize/2;
stepSize = fftFrameSize/osamp;
freqPerBin = sampleRate/(double)fftFrameSize;
expct = 2.*Math_PI*(double)stepSize/(double)fftFrameSize;
inFifoLatency = fftFrameSize-stepSize;
if (gRover == 0) { gRover = inFifoLatency;
}
/* initialize our static arrays */
/* main processing loop */
for (i = 0; i < numSampsToProcess; i++){
/* As long as we have not yet collected enough data just read in */
gInFIFO[gRover] = indata[i*stride];
outdata[i*stride] = gOutFIFO[gRover-inFifoLatency];
gRover++;
/* now we have enough data for processing */
if (gRover >= fftFrameSize) {
gRover = inFifoLatency;
/* do windowing and re,im interleave */
for (k = 0; k < fftFrameSize;k++) {
window = -.5*cos(2.*Math_PI*(double)k/(double)fftFrameSize)+.5;
gFFTworksp[2*k] = gInFIFO[k] * window;
gFFTworksp[2*k+1] = 0.;
}
/* ***************** ANALYSIS ******************* */
/* do transform */
smbFft(gFFTworksp, fftFrameSize, -1);
/* this is the analysis step */
for (k = 0; k <= fftFrameSize2; k++) {
/* de-interlace FFT buffer */
real = gFFTworksp[2*k];
imag = gFFTworksp[2*k+1];
/* compute magnitude and phase */
magn = 2.*sqrt(real*real + imag*imag);
phase = atan2(imag,real);
/* compute phase difference */
tmp = phase - gLastPhase[k];
gLastPhase[k] = phase;
/* subtract expected phase difference */
tmp -= (double)k*expct;
/* map delta phase into +/- Pi interval */
qpd = tmp/Math_PI;
if (qpd >= 0) { qpd += qpd&1;
} else { qpd -= qpd&1;
}
tmp -= Math_PI*(double)qpd;
/* get deviation from bin frequency from the +/- Pi interval */
tmp = osamp*tmp/(2.*Math_PI);
/* compute the k-th partials' true frequency */
tmp = (double)k*freqPerBin + tmp*freqPerBin;
/* store magnitude and true frequency in analysis arrays */
gAnaMagn[k] = magn;
gAnaFreq[k] = tmp;
}
/* ***************** PROCESSING ******************* */
/* this does the actual pitch shifting */
memset(gSynMagn, 0, fftFrameSize*sizeof(float));
memset(gSynFreq, 0, fftFrameSize*sizeof(float));
for (k = 0; k <= fftFrameSize2; k++) {
index = k*pitchShift;
if (index <= fftFrameSize2) {
gSynMagn[index] += gAnaMagn[k];
gSynFreq[index] = gAnaFreq[k] * pitchShift;
}
}
/* ***************** SYNTHESIS ******************* */
/* this is the synthesis step */
for (k = 0; k <= fftFrameSize2; k++) {
/* get magnitude and true frequency from synthesis arrays */
magn = gSynMagn[k];
tmp = gSynFreq[k];
/* subtract bin mid frequency */
tmp -= (double)k*freqPerBin;
/* get bin deviation from freq deviation */
tmp /= freqPerBin;
/* take osamp into account */
tmp = 2.*Math_PI*tmp/osamp;
/* add the overlap phase advance back in */
tmp += (double)k*expct;
/* accumulate delta phase to get bin phase */
gSumPhase[k] += tmp;
phase = gSumPhase[k];
/* get real and imag part and re-interleave */
gFFTworksp[2*k] = magn*cos(phase);
gFFTworksp[2*k+1] = magn*sin(phase);
}
/* zero negative frequencies */
for (k = fftFrameSize+2; k < 2*fftFrameSize; k++) { gFFTworksp[k] = 0.;
}
/* do inverse transform */
smbFft(gFFTworksp, fftFrameSize, 1);
/* do windowing and add to output accumulator */
for(k=0; k < fftFrameSize; k++) {
window = -.5*cos(2.*Math_PI*(double)k/(double)fftFrameSize)+.5;
gOutputAccum[k] += 2.*window*gFFTworksp[2*k]/(fftFrameSize2*osamp);
}
for (k = 0; k < stepSize; k++) { gOutFIFO[k] = gOutputAccum[k];
}
/* shift accumulator */
memmove(gOutputAccum, gOutputAccum+stepSize, fftFrameSize*sizeof(float));
/* move input FIFO */
for (k = 0; k < inFifoLatency; k++) { gInFIFO[k] = gInFIFO[k+stepSize];
}
}
}
}
void SMBPitchShift::smbFft(float *fftBuffer, long fftFrameSize, long sign)
/*
FFT routine, (C)1996 S.M.Bernsee. Sign = -1 is FFT, 1 is iFFT (inverse)
Fills fftBuffer[0...2*fftFrameSize-1] with the Fourier transform of the
time domain data in fftBuffer[0...2*fftFrameSize-1]. The FFT array takes
and returns the cosine and sine parts in an interleaved manner, ie.
fftBuffer[0] = cosPart[0], fftBuffer[1] = sinPart[0], asf. fftFrameSize
must be a power of 2. It expects a complex input signal (see footnote 2),
ie. when working with 'common' audio signals our input signal has to be
passed as {in[0],0.,in[1],0.,in[2],0.,...} asf. In that case, the transform
of the frequencies of interest is in fftBuffer[0...fftFrameSize].
*/
{
float wr, wi, arg, *p1, *p2, temp;<--- The scope of the variable 'wr' can be reduced. [+]The scope of the variable 'wr' can be reduced. Warning: Be careful when fixing this message, especially when there are inner loops. Here is an example where cppcheck will write that the scope for 'i' can be reduced:
void f(int x)
{
int i = 0;
if (x) {
// it's safe to move 'int i = 0;' here
for (int n = 0; n < 10; ++n) {
// it is possible but not safe to move 'int i = 0;' here
do_something(&i);
}
}
}
When you see this message it is always safe to reduce the variable scope 1 level. <--- The scope of the variable 'wi' can be reduced. [+]The scope of the variable 'wi' can be reduced. Warning: Be careful when fixing this message, especially when there are inner loops. Here is an example where cppcheck will write that the scope for 'i' can be reduced:
void f(int x)
{
int i = 0;
if (x) {
// it's safe to move 'int i = 0;' here
for (int n = 0; n < 10; ++n) {
// it is possible but not safe to move 'int i = 0;' here
do_something(&i);
}
}
}
When you see this message it is always safe to reduce the variable scope 1 level. <--- The scope of the variable 'arg' can be reduced. [+]The scope of the variable 'arg' can be reduced. Warning: Be careful when fixing this message, especially when there are inner loops. Here is an example where cppcheck will write that the scope for 'i' can be reduced:
void f(int x)
{
int i = 0;
if (x) {
// it's safe to move 'int i = 0;' here
for (int n = 0; n < 10; ++n) {
// it is possible but not safe to move 'int i = 0;' here
do_something(&i);
}
}
}
When you see this message it is always safe to reduce the variable scope 1 level.
float tr, ti, ur, ui, *p1r, *p1i, *p2r, *p2i;<--- The scope of the variable 'ur' can be reduced. [+]The scope of the variable 'ur' can be reduced. Warning: Be careful when fixing this message, especially when there are inner loops. Here is an example where cppcheck will write that the scope for 'i' can be reduced:
void f(int x)
{
int i = 0;
if (x) {
// it's safe to move 'int i = 0;' here
for (int n = 0; n < 10; ++n) {
// it is possible but not safe to move 'int i = 0;' here
do_something(&i);
}
}
}
When you see this message it is always safe to reduce the variable scope 1 level. <--- The scope of the variable 'ui' can be reduced. [+]The scope of the variable 'ui' can be reduced. Warning: Be careful when fixing this message, especially when there are inner loops. Here is an example where cppcheck will write that the scope for 'i' can be reduced:
void f(int x)
{
int i = 0;
if (x) {
// it's safe to move 'int i = 0;' here
for (int n = 0; n < 10; ++n) {
// it is possible but not safe to move 'int i = 0;' here
do_something(&i);
}
}
}
When you see this message it is always safe to reduce the variable scope 1 level.
long i, bitm, j, le, le2, k;<--- The scope of the variable 'le2' can be reduced. [+]The scope of the variable 'le2' can be reduced. Warning: Be careful when fixing this message, especially when there are inner loops. Here is an example where cppcheck will write that the scope for 'i' can be reduced:
void f(int x)
{
int i = 0;
if (x) {
// it's safe to move 'int i = 0;' here
for (int n = 0; n < 10; ++n) {
// it is possible but not safe to move 'int i = 0;' here
do_something(&i);
}
}
}
When you see this message it is always safe to reduce the variable scope 1 level.
for (i = 2; i < 2*fftFrameSize-2; i += 2) {
for (bitm = 2, j = 0; bitm < 2*fftFrameSize; bitm <<= 1) {
if (i & bitm) { j++;
}
j <<= 1;
}
if (i < j) {
p1 = fftBuffer+i; p2 = fftBuffer+j;
temp = *p1; *(p1++) = *p2;
*(p2++) = temp; temp = *p1;
*p1 = *p2; *p2 = temp;
}
}
for (k = 0, le = 2; k < (long)(log((double)fftFrameSize)/log(2.)+.5); k++) {
le <<= 1;
le2 = le>>1;
ur = 1.0;
ui = 0.0;
arg = Math_PI / (le2>>1);
wr = cos(arg);
wi = sign*sin(arg);
for (j = 0; j < le2; j += 2) {
p1r = fftBuffer+j; p1i = p1r+1;
p2r = p1r+le2; p2i = p2r+1;
for (i = j; i < 2*fftFrameSize; i += le) {
tr = *p2r * ur - *p2i * ui;
ti = *p2r * ui + *p2i * ur;
*p2r = *p1r - tr; *p2i = *p1i - ti;
*p1r += tr; *p1i += ti;
p1r += le; p1i += le;
p2r += le; p2i += le;
}
tr = ur*wr - ui*wi;
ui = ur*wi + ui*wr;
ur = tr;
}
}
}
/* Godot code again */
/* clang-format on */
void AudioEffectPitchShiftInstance::process(const AudioFrame *p_src_frames, AudioFrame *p_dst_frames, int p_frame_count) {
// Avoid distortion by skipping processing if pitch_scale is 1.0.
if (Math::is_equal_approx(base->pitch_scale, 1.0f)) {
return;
}
float sample_rate = AudioServer::get_singleton()->get_mix_rate();
float *in_l = (float *)p_src_frames;
float *in_r = in_l + 1;
float *out_l = (float *)p_dst_frames;
float *out_r = out_l + 1;
shift_l.PitchShift(base->pitch_scale, p_frame_count, fft_size, base->oversampling, sample_rate, in_l, out_l, 2);
shift_r.PitchShift(base->pitch_scale, p_frame_count, fft_size, base->oversampling, sample_rate, in_r, out_r, 2);
}
Ref<AudioEffectInstance> AudioEffectPitchShift::instantiate() {
Ref<AudioEffectPitchShiftInstance> ins;
ins.instantiate();
ins->base = Ref<AudioEffectPitchShift>(this);
static const int fft_sizes[FFT_SIZE_MAX] = { 256, 512, 1024, 2048, 4096 };
ins->fft_size = fft_sizes[fft_size];
return ins;
}
void AudioEffectPitchShift::set_pitch_scale(float p_pitch_scale) {
ERR_FAIL_COND(!(p_pitch_scale > 0.0));
pitch_scale = p_pitch_scale;
}
float AudioEffectPitchShift::get_pitch_scale() const {
return pitch_scale;
}
void AudioEffectPitchShift::set_oversampling(int p_oversampling) {
ERR_FAIL_COND(p_oversampling < 4);
oversampling = p_oversampling;
}
int AudioEffectPitchShift::get_oversampling() const {
return oversampling;
}
void AudioEffectPitchShift::set_fft_size(FFTSize p_fft_size) {
ERR_FAIL_INDEX(p_fft_size, FFT_SIZE_MAX);
fft_size = p_fft_size;
}
AudioEffectPitchShift::FFTSize AudioEffectPitchShift::get_fft_size() const {
return fft_size;
}
void AudioEffectPitchShift::_bind_methods() {
ClassDB::bind_method(D_METHOD("set_pitch_scale", "rate"), &AudioEffectPitchShift::set_pitch_scale);
ClassDB::bind_method(D_METHOD("get_pitch_scale"), &AudioEffectPitchShift::get_pitch_scale);
ClassDB::bind_method(D_METHOD("set_oversampling", "amount"), &AudioEffectPitchShift::set_oversampling);
ClassDB::bind_method(D_METHOD("get_oversampling"), &AudioEffectPitchShift::get_oversampling);
ClassDB::bind_method(D_METHOD("set_fft_size", "size"), &AudioEffectPitchShift::set_fft_size);
ClassDB::bind_method(D_METHOD("get_fft_size"), &AudioEffectPitchShift::get_fft_size);
ADD_PROPERTY(PropertyInfo(Variant::FLOAT, "pitch_scale", PROPERTY_HINT_RANGE, "0.01,16,0.01"), "set_pitch_scale", "get_pitch_scale");
ADD_PROPERTY(PropertyInfo(Variant::FLOAT, "oversampling", PROPERTY_HINT_RANGE, "4,32,1"), "set_oversampling", "get_oversampling");
ADD_PROPERTY(PropertyInfo(Variant::INT, "fft_size", PROPERTY_HINT_ENUM, "256,512,1024,2048,4096"), "set_fft_size", "get_fft_size");
BIND_ENUM_CONSTANT(FFT_SIZE_256);
BIND_ENUM_CONSTANT(FFT_SIZE_512);
BIND_ENUM_CONSTANT(FFT_SIZE_1024);
BIND_ENUM_CONSTANT(FFT_SIZE_2048);
BIND_ENUM_CONSTANT(FFT_SIZE_4096);
BIND_ENUM_CONSTANT(FFT_SIZE_MAX);
}
|