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
|
/*
* Copyright (c) 2012 The WebRTC project authors. All Rights Reserved.
*
* Use of this source code is governed by a BSD-style license
* that can be found in the LICENSE file in the root of the source
* tree. An additional intellectual property rights grant can be found
* in the file PATENTS. All contributing project authors may
* be found in the AUTHORS file in the root of the source tree.
*/
#include "audio/utility/audio_frame_operations.h"
#include <string.h>
#include <algorithm>
#include <cstdint>
#include <utility>
#include "common_audio/include/audio_util.h"
#include "rtc_base/checks.h"
#include "rtc_base/numerics/safe_conversions.h"
namespace webrtc {
namespace {
// 2.7ms @ 48kHz, 4ms @ 32kHz, 8ms @ 16kHz.
const size_t kMuteFadeFrames = 128;
const float kMuteFadeInc = 1.0f / kMuteFadeFrames;
} // namespace
void AudioFrameOperations::QuadToStereo(
InterleavedView<const int16_t> src_audio,
InterleavedView<int16_t> dst_audio) {
RTC_DCHECK_EQ(NumChannels(src_audio), 4);
RTC_DCHECK_EQ(NumChannels(dst_audio), 2);
RTC_DCHECK_EQ(SamplesPerChannel(src_audio), SamplesPerChannel(dst_audio));
for (size_t i = 0; i < SamplesPerChannel(src_audio); ++i) {
auto dst_frame = i * 2;
dst_audio[dst_frame] =
(static_cast<int32_t>(src_audio[4 * i]) + src_audio[4 * i + 1]) >> 1;
dst_audio[dst_frame + 1] =
(static_cast<int32_t>(src_audio[4 * i + 2]) + src_audio[4 * i + 3]) >>
1;
}
}
int AudioFrameOperations::QuadToStereo(AudioFrame* frame) {
if (frame->num_channels_ != 4) {
return -1;
}
RTC_DCHECK_LE(frame->samples_per_channel_ * 4,
AudioFrame::kMaxDataSizeSamples);
if (!frame->muted()) {
// Note that `src` and `dst` will map in to the same buffer, but the call
// to `mutable_data()` changes the layout of `frame`, so `src` and `dst`
// will have different dimensions (important to call `data_view()` first).
auto src = frame->data_view();
auto dst = frame->mutable_data(frame->samples_per_channel_, 2);
QuadToStereo(src, dst);
} else {
frame->num_channels_ = 2;
}
return 0;
}
void AudioFrameOperations::DownmixChannels(
InterleavedView<const int16_t> src_audio,
InterleavedView<int16_t> dst_audio) {
RTC_DCHECK_EQ(SamplesPerChannel(src_audio), SamplesPerChannel(dst_audio));
if (NumChannels(src_audio) > 1 && IsMono(dst_audio)) {
// TODO(tommi): change DownmixInterleavedToMono to support InterleavedView
// and MonoView.
DownmixInterleavedToMono(&src_audio.data()[0], SamplesPerChannel(src_audio),
NumChannels(src_audio), &dst_audio.data()[0]);
} else if (NumChannels(src_audio) == 4 && NumChannels(dst_audio) == 2) {
QuadToStereo(src_audio, dst_audio);
} else {
RTC_DCHECK_NOTREACHED() << "src_channels: " << NumChannels(src_audio)
<< ", dst_channels: " << NumChannels(dst_audio);
}
}
void AudioFrameOperations::DownmixChannels(size_t dst_channels,
AudioFrame* frame) {
RTC_DCHECK_LE(frame->samples_per_channel_ * frame->num_channels_,
AudioFrame::kMaxDataSizeSamples);
if (frame->num_channels_ > 1 && dst_channels == 1) {
if (!frame->muted()) {
DownmixInterleavedToMono(frame->data(), frame->samples_per_channel_,
frame->num_channels_, frame->mutable_data());
}
frame->num_channels_ = 1;
} else if (frame->num_channels_ == 4 && dst_channels == 2) {
int err = QuadToStereo(frame);
RTC_DCHECK_EQ(err, 0);
} else {
RTC_DCHECK_NOTREACHED() << "src_channels: " << frame->num_channels_
<< ", dst_channels: " << dst_channels;
}
}
void AudioFrameOperations::UpmixChannels(size_t target_number_of_channels,
AudioFrame* frame) {
RTC_DCHECK_EQ(frame->num_channels_, 1);
RTC_DCHECK_LE(frame->samples_per_channel_ * target_number_of_channels,
AudioFrame::kMaxDataSizeSamples);
if (frame->num_channels_ != 1 ||
frame->samples_per_channel_ * target_number_of_channels >
AudioFrame::kMaxDataSizeSamples) {
return;
}
if (!frame->muted()) {
// Up-mixing done in place. Going backwards through the frame ensure nothing
// is irrevocably overwritten.
auto frame_data = frame->mutable_data(frame->samples_per_channel_,
target_number_of_channels);
for (int i = frame->samples_per_channel_ - 1; i >= 0; --i) {
for (size_t j = 0; j < target_number_of_channels; ++j) {
frame_data[target_number_of_channels * i + j] = frame_data[i];
}
}
} else {
frame->num_channels_ = target_number_of_channels;
}
}
void AudioFrameOperations::SwapStereoChannels(AudioFrame* frame) {
RTC_DCHECK(frame);
if (frame->num_channels_ != 2 || frame->muted()) {
return;
}
int16_t* frame_data = frame->mutable_data();
for (size_t i = 0; i < frame->samples_per_channel_ * 2; i += 2) {
std::swap(frame_data[i], frame_data[i + 1]);
}
}
void AudioFrameOperations::Mute(AudioFrame* frame,
bool previous_frame_muted,
bool current_frame_muted) {
RTC_DCHECK(frame);
if (!previous_frame_muted && !current_frame_muted) {
// Not muted, don't touch.
} else if (previous_frame_muted && current_frame_muted) {
// Frame fully muted.
size_t total_samples = frame->samples_per_channel_ * frame->num_channels_;
RTC_DCHECK_GE(AudioFrame::kMaxDataSizeSamples, total_samples);
frame->Mute();
} else {
// Fade is a no-op on a muted frame.
if (frame->muted()) {
return;
}
// Limit number of samples to fade, if frame isn't long enough.
size_t count = kMuteFadeFrames;
float inc = kMuteFadeInc;
if (frame->samples_per_channel_ < kMuteFadeFrames) {
count = frame->samples_per_channel_;
if (count > 0) {
inc = 1.0f / count;
}
}
size_t start = 0;
size_t end = count;
float start_g = 0.0f;
if (current_frame_muted) {
// Fade out the last `count` samples of frame.
RTC_DCHECK(!previous_frame_muted);
start = frame->samples_per_channel_ - count;
end = frame->samples_per_channel_;
start_g = 1.0f;
inc = -inc;
} else {
// Fade in the first `count` samples of frame.
RTC_DCHECK(previous_frame_muted);
}
// Perform fade.
int16_t* frame_data = frame->mutable_data();
size_t channels = frame->num_channels_;
for (size_t j = 0; j < channels; ++j) {
float g = start_g;
for (size_t i = start * channels; i < end * channels; i += channels) {
g += inc;
frame_data[i + j] *= g;
}
}
}
}
void AudioFrameOperations::Mute(AudioFrame* frame) {
Mute(frame, true, true);
}
int AudioFrameOperations::ScaleWithSat(float scale, AudioFrame* frame) {
if (frame->muted()) {
return 0;
}
int16_t* frame_data = frame->mutable_data();
for (size_t i = 0; i < frame->samples_per_channel_ * frame->num_channels_;
i++) {
frame_data[i] = saturated_cast<int16_t>(scale * frame_data[i]);
}
return 0;
}
} // namespace webrtc
|
