aboutsummaryrefslogtreecommitdiff
path: root/talk/session/media/currentspeakermonitor_unittest.cc
blob: 6a99973f96994936bcfc49543f92e4c9cb01ab5e (plain)
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
/*
 * libjingle
 * Copyright 2004 Google Inc.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions are met:
 *
 *  1. Redistributions of source code must retain the above copyright notice,
 *     this list of conditions and the following disclaimer.
 *  2. 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.
 *  3. The name of the author may not be used to endorse or promote products
 *     derived from this software without specific prior written permission.
 *
 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``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 AUTHOR 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 "talk/session/media/audiomonitor.h"
#include "talk/session/media/currentspeakermonitor.h"
#include "webrtc/base/gunit.h"
#include "webrtc/base/thread.h"

namespace cricket {

static const uint32 kSsrc1 = 1001;
static const uint32 kSsrc2 = 1002;
static const uint32 kMinTimeBetweenSwitches = 10;
// Due to limited system clock resolution, the CurrentSpeakerMonitor may
// actually require more or less time between switches than that specified
// in the call to set_min_time_between_switches.  To be safe, we sleep for
// 90 ms more than the min time between switches before checking for a switch.
// I am assuming system clocks do not have a coarser resolution than 90 ms.
static const uint32 kSleepTimeBetweenSwitches = 100;

class CurrentSpeakerMonitorTest : public testing::Test,
    public sigslot::has_slots<> {
 public:
  CurrentSpeakerMonitorTest() {
    monitor_ = new CurrentSpeakerMonitor(&source_, NULL);
    // Shrink the minimum time betweeen switches to 10 ms so we don't have to
    // slow down our tests.
    monitor_->set_min_time_between_switches(kMinTimeBetweenSwitches);
    monitor_->SignalUpdate.connect(this, &CurrentSpeakerMonitorTest::OnUpdate);
    current_speaker_ = 0;
    num_changes_ = 0;
    monitor_->Start();
  }

  ~CurrentSpeakerMonitorTest() {
    delete monitor_;
  }

  void SignalAudioMonitor(const AudioInfo& info) {
    source_.SignalAudioMonitor(&source_, info);
  }

 protected:
  AudioSourceContext source_;
  CurrentSpeakerMonitor* monitor_;
  int num_changes_;
  uint32 current_speaker_;

  void OnUpdate(CurrentSpeakerMonitor* monitor, uint32 current_speaker) {
    current_speaker_ = current_speaker;
    num_changes_++;
  }
};

static void InitAudioInfo(AudioInfo* info, int input_level, int output_level) {
  info->input_level = input_level;
  info->output_level = output_level;
}

TEST_F(CurrentSpeakerMonitorTest, NoActiveStreams) {
  AudioInfo info;
  InitAudioInfo(&info, 0, 0);
  SignalAudioMonitor(info);

  EXPECT_EQ(current_speaker_, 0U);
  EXPECT_EQ(num_changes_, 0);
}

TEST_F(CurrentSpeakerMonitorTest, MultipleActiveStreams) {
  AudioInfo info;
  InitAudioInfo(&info, 0, 0);

  info.active_streams.push_back(std::make_pair(kSsrc1, 3));
  info.active_streams.push_back(std::make_pair(kSsrc2, 7));
  SignalAudioMonitor(info);

  // No speaker recognized because the initial sample is treated as possibly
  // just noise and disregarded.
  EXPECT_EQ(current_speaker_, 0U);
  EXPECT_EQ(num_changes_, 0);

  info.active_streams.push_back(std::make_pair(kSsrc1, 3));
  info.active_streams.push_back(std::make_pair(kSsrc2, 7));
  SignalAudioMonitor(info);

  EXPECT_EQ(current_speaker_, kSsrc2);
  EXPECT_EQ(num_changes_, 1);
}

// See: https://code.google.com/p/webrtc/issues/detail?id=2409
TEST_F(CurrentSpeakerMonitorTest, DISABLED_RapidSpeakerChange) {
  AudioInfo info;
  InitAudioInfo(&info, 0, 0);

  info.active_streams.push_back(std::make_pair(kSsrc1, 3));
  info.active_streams.push_back(std::make_pair(kSsrc2, 7));
  SignalAudioMonitor(info);

  EXPECT_EQ(current_speaker_, 0U);
  EXPECT_EQ(num_changes_, 0);

  info.active_streams.push_back(std::make_pair(kSsrc1, 3));
  info.active_streams.push_back(std::make_pair(kSsrc2, 7));
  SignalAudioMonitor(info);

  EXPECT_EQ(current_speaker_, kSsrc2);
  EXPECT_EQ(num_changes_, 1);

  info.active_streams.push_back(std::make_pair(kSsrc1, 9));
  info.active_streams.push_back(std::make_pair(kSsrc2, 1));
  SignalAudioMonitor(info);

  // We expect no speaker change because of the rapid change.
  EXPECT_EQ(current_speaker_, kSsrc2);
  EXPECT_EQ(num_changes_, 1);
}

TEST_F(CurrentSpeakerMonitorTest, SpeakerChange) {
  AudioInfo info;
  InitAudioInfo(&info, 0, 0);

  info.active_streams.push_back(std::make_pair(kSsrc1, 3));
  info.active_streams.push_back(std::make_pair(kSsrc2, 7));
  SignalAudioMonitor(info);

  EXPECT_EQ(current_speaker_, 0U);
  EXPECT_EQ(num_changes_, 0);

  info.active_streams.push_back(std::make_pair(kSsrc1, 3));
  info.active_streams.push_back(std::make_pair(kSsrc2, 7));
  SignalAudioMonitor(info);

  EXPECT_EQ(current_speaker_, kSsrc2);
  EXPECT_EQ(num_changes_, 1);

  // Wait so the changes don't come so rapidly.
  rtc::Thread::SleepMs(kSleepTimeBetweenSwitches);

  info.active_streams.push_back(std::make_pair(kSsrc1, 9));
  info.active_streams.push_back(std::make_pair(kSsrc2, 1));
  SignalAudioMonitor(info);

  EXPECT_EQ(current_speaker_, kSsrc1);
  EXPECT_EQ(num_changes_, 2);
}

TEST_F(CurrentSpeakerMonitorTest, InterwordSilence) {
  AudioInfo info;
  InitAudioInfo(&info, 0, 0);

  info.active_streams.push_back(std::make_pair(kSsrc1, 3));
  info.active_streams.push_back(std::make_pair(kSsrc2, 7));
  SignalAudioMonitor(info);

  EXPECT_EQ(current_speaker_, 0U);
  EXPECT_EQ(num_changes_, 0);

  info.active_streams.push_back(std::make_pair(kSsrc1, 3));
  info.active_streams.push_back(std::make_pair(kSsrc2, 7));
  SignalAudioMonitor(info);

  EXPECT_EQ(current_speaker_, kSsrc2);
  EXPECT_EQ(num_changes_, 1);

  info.active_streams.push_back(std::make_pair(kSsrc1, 3));
  info.active_streams.push_back(std::make_pair(kSsrc2, 7));
  SignalAudioMonitor(info);

  EXPECT_EQ(current_speaker_, kSsrc2);
  EXPECT_EQ(num_changes_, 1);

  // Wait so the changes don't come so rapidly.
  rtc::Thread::SleepMs(kSleepTimeBetweenSwitches);

  info.active_streams.push_back(std::make_pair(kSsrc1, 3));
  info.active_streams.push_back(std::make_pair(kSsrc2, 0));
  SignalAudioMonitor(info);

  // Current speaker shouldn't have changed because we treat this as an inter-
  // word silence.
  EXPECT_EQ(current_speaker_, kSsrc2);
  EXPECT_EQ(num_changes_, 1);

  info.active_streams.push_back(std::make_pair(kSsrc1, 3));
  info.active_streams.push_back(std::make_pair(kSsrc2, 0));
  SignalAudioMonitor(info);

  // Current speaker shouldn't have changed because we treat this as an inter-
  // word silence.
  EXPECT_EQ(current_speaker_, kSsrc2);
  EXPECT_EQ(num_changes_, 1);

  info.active_streams.push_back(std::make_pair(kSsrc1, 3));
  info.active_streams.push_back(std::make_pair(kSsrc2, 0));
  SignalAudioMonitor(info);

  // At this point, we should have concluded that SSRC2 stopped speaking.
  EXPECT_EQ(current_speaker_, kSsrc1);
  EXPECT_EQ(num_changes_, 2);
}

}  // namespace cricket