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
|
// Copyright 2024 The Chromium Authors
// Use of this source code is governed by a BSD-style license that can be
// found in the LICENSE file.
#include "components/speech/speech_recognizer_fsm.h"
#include "base/notreached.h"
#include "components/speech/audio_buffer.h"
#include "media/mojo/mojom/audio_data.mojom.h"
#include "media/mojo/mojom/speech_recognition_error.mojom.h"
#include "media/mojo/mojom/speech_recognition_result.mojom.h"
namespace speech {
SpeechRecognizerFsm::FSMEventArgs::FSMEventArgs(FSMEvent event_value)
: event(event_value),
engine_error(media::mojom::SpeechRecognitionErrorCode::kNone,
media::mojom::SpeechAudioErrorDetails::kNone) {}
SpeechRecognizerFsm::FSMEventArgs::FSMEventArgs(const FSMEventArgs& other)
: event(other.event),
audio_data(other.audio_data ? other.audio_data->Clone() : nullptr),
audio_chunk(other.audio_chunk),
recognition_context(other.recognition_context),
engine_error(other.engine_error) {
engine_results = mojo::Clone(other.engine_results);
}
SpeechRecognizerFsm::FSMEventArgs::~FSMEventArgs() = default;
SpeechRecognizerFsm::FSMState
SpeechRecognizerFsm::ExecuteTransitionAndGetNextState(
const FSMEventArgs& event_args) {
const FSMEvent event = event_args.event;
switch (state_) {
case STATE_IDLE:
switch (event) {
case EVENT_ABORT:
return AbortSilently(event_args);
case EVENT_PREPARE:
return PrepareRecognition(event_args);
case EVENT_START:
return NotFeasible(event_args);
case EVENT_STOP_CAPTURE:
return AbortSilently(event_args);
case EVENT_UPDATE_RECOGNITION_CONTEXT:
return UpdateRecognitionContext(event_args);
case EVENT_AUDIO_DATA: // Corner cases related to queued messages
case EVENT_ENGINE_RESULT: // being lately dispatched.
case EVENT_ENGINE_ERROR:
case EVENT_AUDIO_ERROR:
return DoNothing(event_args);
}
break;
case STATE_PREPARING:
switch (event) {
case EVENT_ABORT:
return AbortSilently(event_args);
case EVENT_PREPARE:
return NotFeasible(event_args);
case EVENT_START:
return StartRecording(event_args);
case EVENT_STOP_CAPTURE:
return AbortSilently(event_args);
case EVENT_UPDATE_RECOGNITION_CONTEXT:
return UpdateRecognitionContext(event_args);
case EVENT_AUDIO_DATA: // Corner cases related to queued messages
case EVENT_ENGINE_RESULT: // being lately dispatched.
case EVENT_ENGINE_ERROR:
case EVENT_AUDIO_ERROR:
return DoNothing(event_args);
}
break;
case STATE_STARTING:
switch (event) {
case EVENT_ABORT:
return AbortWithError(event_args);
case EVENT_PREPARE:
return NotFeasible(event_args);
case EVENT_START:
return NotFeasible(event_args);
case EVENT_STOP_CAPTURE:
return AbortSilently(event_args);
case EVENT_AUDIO_DATA:
return StartRecognitionEngine(event_args);
case EVENT_ENGINE_RESULT:
if (event_args.audio_data) {
return ProcessIntermediateResult(event_args);
}
return NotFeasible(event_args);
case EVENT_UPDATE_RECOGNITION_CONTEXT:
return UpdateRecognitionContext(event_args);
case EVENT_ENGINE_ERROR:
case EVENT_AUDIO_ERROR:
return AbortWithError(event_args);
}
break;
case STATE_ESTIMATING_ENVIRONMENT:
switch (event) {
case EVENT_ABORT:
return AbortWithError(event_args);
case EVENT_PREPARE:
return NotFeasible(event_args);
case EVENT_START:
return NotFeasible(event_args);
case EVENT_STOP_CAPTURE:
return StopCaptureAndWaitForResult(event_args);
case EVENT_AUDIO_DATA:
return WaitEnvironmentEstimationCompletion(event_args);
case EVENT_ENGINE_RESULT:
return ProcessIntermediateResult(event_args);
case EVENT_UPDATE_RECOGNITION_CONTEXT:
return UpdateRecognitionContext(event_args);
case EVENT_ENGINE_ERROR:
case EVENT_AUDIO_ERROR:
return AbortWithError(event_args);
}
break;
case STATE_WAITING_FOR_SPEECH:
switch (event) {
case EVENT_ABORT:
return AbortWithError(event_args);
case EVENT_PREPARE:
return NotFeasible(event_args);
case EVENT_START:
return NotFeasible(event_args);
case EVENT_STOP_CAPTURE:
return StopCaptureAndWaitForResult(event_args);
case EVENT_AUDIO_DATA:
return DetectUserSpeechOrTimeout(event_args);
case EVENT_ENGINE_RESULT:
return ProcessIntermediateResult(event_args);
case EVENT_UPDATE_RECOGNITION_CONTEXT:
return UpdateRecognitionContext(event_args);
case EVENT_ENGINE_ERROR:
case EVENT_AUDIO_ERROR:
return AbortWithError(event_args);
}
break;
case STATE_RECOGNIZING:
switch (event) {
case EVENT_ABORT:
return AbortWithError(event_args);
case EVENT_PREPARE:
return NotFeasible(event_args);
case EVENT_START:
return NotFeasible(event_args);
case EVENT_STOP_CAPTURE:
return StopCaptureAndWaitForResult(event_args);
case EVENT_AUDIO_DATA:
return DetectEndOfSpeech(event_args);
case EVENT_ENGINE_RESULT:
return ProcessIntermediateResult(event_args);
case EVENT_UPDATE_RECOGNITION_CONTEXT:
return UpdateRecognitionContext(event_args);
case EVENT_ENGINE_ERROR:
case EVENT_AUDIO_ERROR:
return AbortWithError(event_args);
}
break;
case STATE_WAITING_FINAL_RESULT:
switch (event) {
case EVENT_ABORT:
return AbortWithError(event_args);
case EVENT_PREPARE:
return NotFeasible(event_args);
case EVENT_START:
return NotFeasible(event_args);
case EVENT_STOP_CAPTURE:
case EVENT_AUDIO_DATA:
return DoNothing(event_args);
case EVENT_ENGINE_RESULT:
return ProcessFinalResult(event_args);
case EVENT_UPDATE_RECOGNITION_CONTEXT:
return UpdateRecognitionContext(event_args);
case EVENT_ENGINE_ERROR:
case EVENT_AUDIO_ERROR:
return AbortWithError(event_args);
}
break;
case STATE_ENDED:
return DoNothing(event_args);
}
NOTREACHED();
}
} // namespace speech
|
