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
|
/*
* libjingle
* Copyright 2011 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/currentspeakermonitor.h"
#include "talk/media/base/streamparams.h"
#include "talk/session/media/audiomonitor.h"
#include "talk/session/media/mediamessages.h"
#include "webrtc/base/logging.h"
namespace cricket {
namespace {
const int kMaxAudioLevel = 9;
// To avoid overswitching, we disable switching for a period of time after a
// switch is done.
const int kDefaultMinTimeBetweenSwitches = 1000;
}
CurrentSpeakerMonitor::CurrentSpeakerMonitor(
AudioSourceContext* audio_source_context, BaseSession* session)
: started_(false),
audio_source_context_(audio_source_context),
session_(session),
current_speaker_ssrc_(0),
earliest_permitted_switch_time_(0),
min_time_between_switches_(kDefaultMinTimeBetweenSwitches) {
}
CurrentSpeakerMonitor::~CurrentSpeakerMonitor() {
Stop();
}
void CurrentSpeakerMonitor::Start() {
if (!started_) {
audio_source_context_->SignalAudioMonitor.connect(
this, &CurrentSpeakerMonitor::OnAudioMonitor);
audio_source_context_->SignalMediaStreamsUpdate.connect(
this, &CurrentSpeakerMonitor::OnMediaStreamsUpdate);
audio_source_context_->SignalMediaStreamsReset.connect(
this, &CurrentSpeakerMonitor::OnMediaStreamsReset);
started_ = true;
}
}
void CurrentSpeakerMonitor::Stop() {
if (started_) {
audio_source_context_->SignalAudioMonitor.disconnect(this);
audio_source_context_->SignalMediaStreamsUpdate.disconnect(this);
started_ = false;
ssrc_to_speaking_state_map_.clear();
current_speaker_ssrc_ = 0;
earliest_permitted_switch_time_ = 0;
}
}
void CurrentSpeakerMonitor::set_min_time_between_switches(
uint32 min_time_between_switches) {
min_time_between_switches_ = min_time_between_switches;
}
void CurrentSpeakerMonitor::OnAudioMonitor(
AudioSourceContext* audio_source_context, const AudioInfo& info) {
std::map<uint32, int> active_ssrc_to_level_map;
cricket::AudioInfo::StreamList::const_iterator stream_list_it;
for (stream_list_it = info.active_streams.begin();
stream_list_it != info.active_streams.end(); ++stream_list_it) {
uint32 ssrc = stream_list_it->first;
active_ssrc_to_level_map[ssrc] = stream_list_it->second;
// It's possible we haven't yet added this source to our map. If so,
// add it now with a "not speaking" state.
if (ssrc_to_speaking_state_map_.find(ssrc) ==
ssrc_to_speaking_state_map_.end()) {
ssrc_to_speaking_state_map_[ssrc] = SS_NOT_SPEAKING;
}
}
int max_level = 0;
uint32 loudest_speaker_ssrc = 0;
// Update the speaking states of all participants based on the new audio
// level information. Also retain loudest speaker.
std::map<uint32, SpeakingState>::iterator state_it;
for (state_it = ssrc_to_speaking_state_map_.begin();
state_it != ssrc_to_speaking_state_map_.end(); ++state_it) {
bool is_previous_speaker = current_speaker_ssrc_ == state_it->first;
// This uses a state machine in order to gradually identify
// members as having started or stopped speaking. Matches the
// algorithm used by the hangouts js code.
std::map<uint32, int>::const_iterator level_it =
active_ssrc_to_level_map.find(state_it->first);
// Note that the stream map only contains streams with non-zero audio
// levels.
int level = (level_it != active_ssrc_to_level_map.end()) ?
level_it->second : 0;
switch (state_it->second) {
case SS_NOT_SPEAKING:
if (level > 0) {
// Reset level because we don't think they're really speaking.
level = 0;
state_it->second = SS_MIGHT_BE_SPEAKING;
} else {
// State unchanged.
}
break;
case SS_MIGHT_BE_SPEAKING:
if (level > 0) {
state_it->second = SS_SPEAKING;
} else {
state_it->second = SS_NOT_SPEAKING;
}
break;
case SS_SPEAKING:
if (level > 0) {
// State unchanged.
} else {
state_it->second = SS_WAS_SPEAKING_RECENTLY1;
if (is_previous_speaker) {
// Assume this is an inter-word silence and assign him the highest
// volume.
level = kMaxAudioLevel;
}
}
break;
case SS_WAS_SPEAKING_RECENTLY1:
if (level > 0) {
state_it->second = SS_SPEAKING;
} else {
state_it->second = SS_WAS_SPEAKING_RECENTLY2;
if (is_previous_speaker) {
// Assume this is an inter-word silence and assign him the highest
// volume.
level = kMaxAudioLevel;
}
}
break;
case SS_WAS_SPEAKING_RECENTLY2:
if (level > 0) {
state_it->second = SS_SPEAKING;
} else {
state_it->second = SS_NOT_SPEAKING;
}
break;
}
if (level > max_level) {
loudest_speaker_ssrc = state_it->first;
max_level = level;
} else if (level > 0 && level == max_level && is_previous_speaker) {
// Favor continuity of loudest speakers if audio levels are equal.
loudest_speaker_ssrc = state_it->first;
}
}
// We avoid over-switching by disabling switching for a period of time after
// a switch is done.
uint32 now = rtc::Time();
if (earliest_permitted_switch_time_ <= now &&
current_speaker_ssrc_ != loudest_speaker_ssrc) {
current_speaker_ssrc_ = loudest_speaker_ssrc;
LOG(LS_INFO) << "Current speaker changed to " << current_speaker_ssrc_;
earliest_permitted_switch_time_ = now + min_time_between_switches_;
SignalUpdate(this, current_speaker_ssrc_);
}
}
void CurrentSpeakerMonitor::OnMediaStreamsUpdate(
AudioSourceContext* audio_source_context, BaseSession* session,
const MediaStreams& added, const MediaStreams& removed) {
if (audio_source_context == audio_source_context_ && session == session_) {
// Update the speaking state map based on added and removed streams.
for (std::vector<cricket::StreamParams>::const_iterator
it = removed.audio().begin(); it != removed.audio().end(); ++it) {
ssrc_to_speaking_state_map_.erase(it->first_ssrc());
}
for (std::vector<cricket::StreamParams>::const_iterator
it = added.audio().begin(); it != added.audio().end(); ++it) {
ssrc_to_speaking_state_map_[it->first_ssrc()] = SS_NOT_SPEAKING;
}
}
}
void CurrentSpeakerMonitor::OnMediaStreamsReset(
AudioSourceContext* audio_source_context, BaseSession* session) {
if (audio_source_context == audio_source_context_ && session == session_) {
ssrc_to_speaking_state_map_.clear();
}
}
} // namespace cricket
|
