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
|
/****************************************************************************
**
** Copyright (C) 2012 Nokia Corporation and/or its subsidiary(-ies).
** Contact: http://www.qt-project.org/
**
** This file is part of the QtDeclarative module of the Qt Toolkit.
**
** $QT_BEGIN_LICENSE:BSD$
** You may use this file under the terms of the BSD license as follows:
**
** "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.
** * Neither the name of Nokia Corporation and its Subsidiary(-ies) nor
** the names of its contributors may be used to endorse or promote
** products derived from this software without specific prior written
** permission.
**
** 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
** OWNER 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."
**
** $QT_END_LICENSE$
**
****************************************************************************/
#include "voiceanalyzer.h"
/**
* Constant used to scale the cut-off density for the fft helper.
*/
const static float CutOffScaler = 0.05;
/**
* Force the precision to be "1/PrecisionPerNote" notes
* near the target frequency.
*/
const static int PrecisionPerNote = 4;
/**
* TargetFrequencyParameter is a constant which implies the index at
* which corresponds to the target frequency.
* 0.5 * N * 1/TargetFrequencyParameter is (about) the index which
* corresponds to the given target frequency.
* Effectively TargetFrequencyParameter = 2^z, and the z*TargetFrequency
* is the maximum frequency that can be noticed.
*/
const static int TargetFrequencyParameter = 4;
VoiceAnalyzer::VoiceAnalyzer(const QAudioFormat &format, QObject *parent):
QIODevice(parent),
m_format(format),
m_frequency(0),
m_position(0),
m_fftHelper(new FastFourierTransformer(this))
{
Q_ASSERT(qFuzzyCompare(M_SAMPLE_COUNT_MULTIPLIER,
float(2)/(M_TWELTH_ROOT_OF_2 -1.0)));
m_totalSampleCount = qRound(qreal(PrecisionPerNote)
*TargetFrequencyParameter
*M_SAMPLE_COUNT_MULTIPLIER);
m_samples.reserve(m_totalSampleCount);
int i = 2;
int j = 1;
for (; i < TargetFrequencyParameter; i *= 2) {
j++;
}
m_maximumVoiceDifference = j*12;
setCutOffPercentage(CutOffScaler);
}
/**
* Opens the parent QIODevice. Sets up the analysation parameters.
*/
void VoiceAnalyzer::start(qreal frequency)
{
m_stepSize = (qreal) 1.0 * m_format.sampleRate()
/ (TargetFrequencyParameter*2*frequency);
m_frequency = frequency;
open(QIODevice::WriteOnly);
}
/**
* Closes the parent QIODevice, thus the voice is not analysed anymore.
* Resets the m_samples QList.
*/
void VoiceAnalyzer::stop()
{
m_samples.clear();
m_samples.reserve(m_totalSampleCount);
close();
}
/**
* Called when data is obtained. Stores each m_stepSize sample
* into a QList to be analysed.
*/
qint64 VoiceAnalyzer::writeData(const char *data, qint64 maxlen)
{
const int channelBytes = m_format.sampleSize() / 8;
int sampleSize = m_format.channels() * channelBytes;
int m_stepSizeInBytes = m_stepSize*sampleSize;
// assert that each sample fits fully into the data
Q_ASSERT((m_position % sampleSize)==0);
const uchar *ptr = reinterpret_cast<const uchar *>(data);
while (m_position < maxlen) {
if (m_samples.size() < m_totalSampleCount) {
m_samples.append(getValueInt16(ptr+m_position));
}
else {
analyzeVoice();
m_samples.clear();
m_samples.reserve(m_totalSampleCount);
// fast forward position to the first position after maxlen or to the maxlen
m_position += ((m_stepSizeInBytes - 1 + maxlen - m_position) /
m_stepSizeInBytes) * m_stepSizeInBytes;
break;
}
m_position += m_stepSizeInBytes;
}
m_position -= maxlen;
return maxlen;
}
/**
* Interprets ptr as a pointer to int value and returns it.
*/
qint16 VoiceAnalyzer::getValueInt16(const uchar *ptr)
{
qint16 realValue = 0;
if (m_format.sampleSize() == 8)
{
const qint16 value = *reinterpret_cast<const quint8*>(ptr);
if (m_format.sampleType() == QAudioFormat::UnSignedInt) {
realValue = value - M_MAX_AMPLITUDE_8BIT_SIGNED - 1;
} else if (m_format.sampleType() == QAudioFormat::SignedInt) {
realValue = value;
}
} else if (m_format.sampleSize() == 16) {
qint16 value = 0;
if (m_format.byteOrder() == QAudioFormat::LittleEndian)
value = qFromLittleEndian<quint16>(ptr);
else
value = qFromBigEndian<quint16>(ptr);
if (m_format.sampleType() == QAudioFormat::UnSignedInt) {
realValue = value - M_MAX_AMPLITUDE_16BIT_SIGNED;
} else if (m_format.sampleType() == QAudioFormat::SignedInt) {
realValue = value;
}
}
return realValue;
}
/**
* Takes a number between 0 and 1, scales it with CutOffScaler,
* multiplies it with maximum density, and then gives it
* to the fft helper.
*/
void VoiceAnalyzer::setCutOffPercentage(qreal cutoff)
{
cutoff = CutOffScaler*cutoff;
if (m_format.sampleSize() == 8) {
float t = cutoff*m_totalSampleCount*M_MAX_AMPLITUDE_8BIT_SIGNED;
m_fftHelper->setCutOffForDensity(t);
}
else if (m_format.sampleSize() == 16) {
float t = cutoff*m_totalSampleCount*M_MAX_AMPLITUDE_16BIT_SIGNED;
m_fftHelper->setCutOffForDensity(t);
}
}
/**
* Returns the current target frequency.
*/
qreal VoiceAnalyzer::frequency()
{
return m_frequency;
}
/**
* Returns the maximum absolute value sent by
* the voiceDifference() signal.
*/
int VoiceAnalyzer::getMaximumVoiceDifference()
{
return m_maximumVoiceDifference;
}
/**
* Returns the maximum precision per note
* near the target frequency.
*/
int VoiceAnalyzer::getMaximumPrecisionPerNote()
{
return PrecisionPerNote;
}
/**
* Analyzes the voice frequency and emits appropriate signals.
*/
void VoiceAnalyzer::analyzeVoice()
{
m_fftHelper->calculateFFT(m_samples);
int index = m_fftHelper->getMaximumDensityIndex();
// If index == -1
if (index == -1) {
// The voice is to be filtered away.
// Emit the lowVoice signal and return.
emit lowVoice();
qDebug() << "low voice";
return;
}
// Else, continue
// Let the correctIndex to be
// the nearest index corresponding to the correct frequency.
qreal stepSizeInFrequency = (qreal)m_format.sampleRate()
/ (m_totalSampleCount * m_stepSize);
qreal newFrequency = qreal(index) * stepSizeInFrequency;
// Calculate the nearest index corresponding to the correct frequency.
int correctIndex = qRound(m_frequency / stepSizeInFrequency);
qreal value = 0;
// If the obtained frequency is more than
// log_2(TargetFrequencyParameter) octaves less than the m_frequency:
// Note:
// Instead of m_frequency/TargetFrequencyParameter > newFrequency,
// the comparison is done without a div instructions by
// m_frequency > newFrequency * TargetFrequencyParameter.
if (m_frequency > newFrequency * TargetFrequencyParameter) {
// Set the difference value to be -m_maximumVoiceDifference.
qDebug() << "compare" << "low" << newFrequency << m_frequency - stepSizeInFrequency * correctIndex << (m_frequency - stepSizeInFrequency * correctIndex) / stepSizeInFrequency;
value = -m_maximumVoiceDifference;
}
// Else, if the obtained frequency is more than
// log_2(TargetFrequencyParameter) octaves more than the m_frequency:
else if (m_frequency*TargetFrequencyParameter < newFrequency) {
// Set the difference value to be m_maximumVoiceDifference.
qDebug() << "compare" << "high" << newFrequency << m_frequency - stepSizeInFrequency * correctIndex << (m_frequency - stepSizeInFrequency * correctIndex) / stepSizeInFrequency;
value = m_maximumVoiceDifference;
}
// Else:
else {
// Calculate the difference between the obtained and the correct
// frequency in tones.
// Use stepSizeInFrequency * correctIndex instead of
// m_frequency so that the value is zero when there is correct
// voice obtained. Set the difference value to be
// log(frequency / target frequency) * 12 / log(2).
value = log(newFrequency / (stepSizeInFrequency * correctIndex))
* 12 / M_LN2;
qDebug() << "compare" << value << newFrequency << m_frequency - stepSizeInFrequency * correctIndex << (m_frequency - stepSizeInFrequency * correctIndex) / stepSizeInFrequency;
}
// Emit voiceDifference signal.
QVariant valueVar(value); //Has to be QVariant for QML
emit voiceDifference(valueVar);
// If the correctIndex is index, emit the correctFrequency signal.
if (correctIndex == index) {
emit(correctFrequency());
}
}
/**
* Empty implementation for readData, since no data is provided
* by the VoiceAnalyzer class.
*/
qint64 VoiceAnalyzer::readData(char *data, qint64 maxlen)
{
Q_UNUSED(data);
Q_UNUSED(maxlen);
return 0;
}
|