blob: dcca34d71c7fcbfa32395631723769ad02d17dcf (
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
|
/*
* Copyright (C) 2014 The Android Open Source Project
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
#ifndef ANDROID_SOUND_TRIGGER_H
#define ANDROID_SOUND_TRIGGER_H
#include <stdbool.h>
#include <system/audio.h>
#define SOUND_TRIGGER_MAX_STRING_LEN 64 /* max length of strings in properties or
descriptor structs */
#define SOUND_TRIGGER_MAX_LOCALE_LEN 6 /* max length of locale string. e.g en_US */
#define SOUND_TRIGGER_MAX_USERS 10 /* max number of concurrent users */
#define SOUND_TRIGGER_MAX_PHRASES 10 /* max number of concurrent phrases */
#define RECOGNITION_MODE_VOICE_TRIGGER 0x1 /* simple voice trigger */
#define RECOGNITION_MODE_USER_IDENTIFICATION 0x2 /* trigger only if one user in model identified */
#define RECOGNITION_MODE_USER_AUTHENTICATION 0x4 /* trigger only if one user in mode
authenticated */
#define RECOGNITION_STATUS_SUCCESS 0
#define RECOGNITION_STATUS_ABORT 1
#define RECOGNITION_STATUS_FAILURE 2
#define SOUND_MODEL_STATUS_UPDATED 0
typedef enum {
SOUND_MODEL_TYPE_UNKNOWN = -1, /* use for unspecified sound model type */
SOUND_MODEL_TYPE_KEYPHRASE = 0 /* use for key phrase sound models */
} sound_trigger_sound_model_type_t;
typedef struct sound_trigger_uuid_s {
unsigned int timeLow;
unsigned short timeMid;
unsigned short timeHiAndVersion;
unsigned short clockSeq;
unsigned char node[6];
} sound_trigger_uuid_t;
/*
* sound trigger implementation descriptor read by the framework via get_properties().
* Used by SoundTrigger service to report to applications and manage concurrency and policy.
*/
struct sound_trigger_properties {
char implementor[SOUND_TRIGGER_MAX_STRING_LEN]; /* implementor name */
char description[SOUND_TRIGGER_MAX_STRING_LEN]; /* implementation description */
unsigned int version; /* implementation version */
sound_trigger_uuid_t uuid; /* unique implementation ID.
Must change with version each version */
unsigned int max_sound_models; /* maximum number of concurrent sound models
loaded */
unsigned int max_key_phrases; /* maximum number of key phrases */
unsigned int max_users; /* maximum number of concurrent users detected */
unsigned int recognition_modes; /* all supported modes.
e.g RECOGNITION_MODE_VOICE_TRIGGER */
bool capture_transition; /* supports seamless transition from detection
to capture */
unsigned int max_buffer_ms; /* maximum buffering capacity in ms if
capture_transition is true*/
bool concurrent_capture; /* supports capture by other use cases while
detection is active */
unsigned int power_consumption_mw; /* Rated power consumption when detection is active
with TDB silence/sound/speech ratio */
};
typedef int sound_trigger_module_handle_t;
struct sound_trigger_module_descriptor {
sound_trigger_module_handle_t handle;
struct sound_trigger_properties properties;
};
typedef int sound_model_handle_t;
/*
* Generic sound model descriptor. This struct is the header of a larger block passed to
* load_sound_model() and containing the binary data of the sound model.
* Proprietary representation of users in binary data must match information indicated
* by users field
*/
struct sound_trigger_sound_model {
sound_trigger_sound_model_type_t type; /* model type. e.g. SOUND_MODEL_TYPE_KEYPHRASE */
sound_trigger_uuid_t uuid; /* unique sound model ID. */
sound_trigger_uuid_t vendor_uuid; /* unique vendor ID. Identifies the engine the
sound model was build for */
unsigned int data_size; /* size of opaque model data */
unsigned int data_offset; /* offset of opaque data start from head of struct
(e.g sizeof struct sound_trigger_sound_model) */
};
/* key phrase descriptor */
struct sound_trigger_phrase {
unsigned int id; /* keyphrase ID */
unsigned int recognition_mode; /* recognition modes supported by this key phrase */
unsigned int num_users; /* number of users in the key phrase */
unsigned int users[SOUND_TRIGGER_MAX_USERS]; /* users ids: (not uid_t but sound trigger
specific IDs */
char locale[SOUND_TRIGGER_MAX_LOCALE_LEN]; /* locale - JAVA Locale style (e.g. en_US) */
char text[SOUND_TRIGGER_MAX_STRING_LEN]; /* phrase text in UTF-8 format. */
};
/*
* Specialized sound model for key phrase detection.
* Proprietary representation of key phrases in binary data must match information indicated
* by phrases field
*/
struct sound_trigger_phrase_sound_model {
struct sound_trigger_sound_model common;
unsigned int num_phrases; /* number of key phrases in model */
struct sound_trigger_phrase phrases[SOUND_TRIGGER_MAX_PHRASES];
};
/*
* Generic recognition event sent via recognition callback
*/
struct sound_trigger_recognition_event {
int status; /* recognition status e.g.
RECOGNITION_STATUS_SUCCESS */
sound_trigger_sound_model_type_t type; /* event type, same as sound model type.
e.g. SOUND_MODEL_TYPE_KEYPHRASE */
sound_model_handle_t model; /* loaded sound model that triggered the
event */
bool capture_available; /* it is possible to capture audio from this
utterance buffered by the
implementation */
int capture_session; /* audio session ID. framework use */
int capture_delay_ms; /* delay in ms between end of model
detection and start of audio available
for capture. A negative value is possible
(e.g. if key phrase is also available for
capture */
int capture_preamble_ms; /* duration in ms of audio captured
before the start of the trigger.
0 if none. */
unsigned int data_size; /* size of opaque event data */
unsigned int data_offset; /* offset of opaque data start from start of
this struct (e.g sizeof struct
sound_trigger_phrase_recognition_event) */
};
/*
* Confidence level for each user in struct sound_trigger_phrase_recognition_extra
*/
struct sound_trigger_confidence_level {
unsigned int user_id; /* user ID */
unsigned int level; /* confidence level in percent (0 - 100).
- min level for recognition configuration
- detected level for recognition event */
};
/*
* Specialized recognition event for key phrase detection
*/
struct sound_trigger_phrase_recognition_extra {
unsigned int id; /* keyphrase ID */
unsigned int recognition_modes; /* recognition modes used for this keyphrase */
unsigned int num_levels; /* number of user confidence levels */
struct sound_trigger_confidence_level levels[SOUND_TRIGGER_MAX_USERS];
};
struct sound_trigger_phrase_recognition_event {
struct sound_trigger_recognition_event common;
bool key_phrase_in_capture; /* true if the key phrase is
present in audio data available
for capture after recognition
event is fired */
unsigned int num_phrases;
struct sound_trigger_phrase_recognition_extra phrase_extras[SOUND_TRIGGER_MAX_PHRASES];
};
/*
* configuration for sound trigger capture session passed to start_recognition()
*/
struct sound_trigger_recognition_config {
audio_io_handle_t capture_handle; /* IO handle that will be used for capture.
N/A if capture_requested is false */
audio_devices_t capture_device; /* input device requested for detection capture */
bool capture_requested; /* capture and buffer audio for this recognition
instance */
unsigned int num_phrases; /* number of key phrases recognition extras */
struct sound_trigger_phrase_recognition_extra phrases[SOUND_TRIGGER_MAX_PHRASES];
/* configuration for each key phrase */
unsigned int data_size; /* size of opaque capture configuration data */
unsigned int data_offset; /* offset of opaque data start from start of this struct
(e.g sizeof struct sound_trigger_recognition_config) */
};
/*
* Event sent via load sound model callback
*/
struct sound_trigger_model_event {
int status; /* sound model status e.g. SOUND_MODEL_STATUS_UPDATED */
unsigned int data_size; /* size of event data if any. Size of updated sound model if
status is SOUND_MODEL_STATUS_UPDATED */
unsigned int data_offset; /* offset of data start from start of this struct
(e.g sizeof struct sound_trigger_model_event) */
};
#endif // ANDROID_SOUND_TRIGGER_H
|
