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
|
/**
* @file llvoicevisualizer.h
* @brief Draws in-world speaking indicators.
*
* Copyright (c) 2000-2007, Linden Research, Inc.
*
* Second Life Viewer Source Code
* The source code in this file ("Source Code") is provided by Linden Lab
* to you under the terms of the GNU General Public License, version 2.0
* ("GPL"), unless you have obtained a separate licensing agreement
* ("Other License"), formally executed by you and Linden Lab. Terms of
* the GPL can be found in doc/GPL-license.txt in this distribution, or
* online at http://secondlife.com/developers/opensource/gplv2
*
* There are special exceptions to the terms and conditions of the GPL as
* it is applied to this Source Code. View the full text of the exception
* in the file doc/FLOSS-exception.txt in this software distribution, or
* online at http://secondlife.com/developers/opensource/flossexception
*
* By copying, modifying or distributing this software, you acknowledge
* that you have read and understood your obligations described above,
* and agree to abide by those obligations.
*
* ALL LINDEN LAB SOURCE CODE IS PROVIDED "AS IS." LINDEN LAB MAKES NO
* WARRANTIES, EXPRESS, IMPLIED OR OTHERWISE, REGARDING ITS ACCURACY,
* COMPLETENESS OR PERFORMANCE.
*/
//--------------------------------------------------------------------
//
// VOICE VISUALIZER
// author: JJ Ventrella, Linden Lab
// (latest update to this info: Jan 18, 2007)
//
// The Voice Visualizer is responsible for taking realtime signals from actual users speaking and
// visualizing this speech in two forms:
//
// (1) as a dynamic sound symbol (also referred to as the "voice indicator" that appears over the avatar's head
// (2) as gesticulation events that are used to trigger avatr gestures
//
// The input for the voice visualizer is a continual stream of voice amplitudes.
//-----------------------------------------------------------------------------
#ifndef LL_VOICE_VISUALIZER_H
#define LL_VOICE_VISUALIZER_H
#include "llhudeffect.h"
//-----------------------------------------------------------------------------------------------
// The values of voice gesticulation represent energy levels for avatar animation, based on
// amplitude surge events parsed from the voice signal. These are made available so that
// the appropriate kind of avatar animation can be triggered, and thereby simulate the physical
// motion effects of speech. It is recommended that multiple body parts be animated as well as
// lips, such as head, shoulders, and hands, with large gestures used when the energy level is high.
//-----------------------------------------------------------------------------------------------
enum VoiceGesticulationLevel
{
VOICE_GESTICULATION_LEVEL_OFF = -1,
VOICE_GESTICULATION_LEVEL_LOW = 0,
VOICE_GESTICULATION_LEVEL_MEDIUM,
VOICE_GESTICULATION_LEVEL_HIGH,
NUM_VOICE_GESTICULATION_LEVELS
};
const static int NUM_VOICE_SYMBOL_WAVES = 7;
//----------------------------------------------------
// LLVoiceVisualizer class
//----------------------------------------------------
class LLVoiceVisualizer : public LLHUDEffect
{
//---------------------------------------------------
// public methods
//---------------------------------------------------
public:
LLVoiceVisualizer ( const U8 type ); //constructor
~LLVoiceVisualizer(); //destructor
friend class LLHUDObject;
void setVoiceSourceWorldPosition( const LLVector3 &p ); // this should be the position of the speaking avatar's head
void setMinGesticulationAmplitude( F32 ); // the lower range of meaningful amplitude for setting gesticulation level
void setMaxGesticulationAmplitude( F32 ); // the upper range of meaningful amplitude for setting gesticulation level
void setStartSpeaking(); // tell me when the av starts speaking
void setVoiceEnabled( bool ); // tell me whether or not the user is voice enabled
void setSpeakingAmplitude( F32 ); // tell me how loud the av is speaking (ranges from 0 to 1)
void setStopSpeaking(); // tell me when the av stops speaking
bool getCurrentlySpeaking(); // the get for the above set
VoiceGesticulationLevel getCurrentGesticulationLevel(); // based on voice amplitude, I'll give you the current "energy level" of avatar speech
void render(); // inherited from HUD Effect
void packData(LLMessageSystem *mesgsys); // inherited from HUD Effect
void unpackData(LLMessageSystem *mesgsys, S32 blocknum); // inherited from HUD Effect
void markDead(); // inherited from HUD Effect
//----------------------------------------------------------------------------------------------
// "setMaxGesticulationAmplitude" and "setMinGesticulationAmplitude" allow for the tuning of the
// gesticulation level detector to be responsive to different kinds of signals. For instance, we
// may find that the average voice amplitude rarely exceeds 0.7 (in a range from 0 to 1), and
// therefore we may want to set 0.7 as the max, so we can more easily catch all the variance
// within that range. Also, we may find that there is often noise below a certain range like 0.1,
// and so we would want to set 0.1 as the min so as not to accidentally use this as signal.
//----------------------------------------------------------------------------------------------
void setMaxGesticulationAmplitude();
void setMinGesticulationAmplitude();
//---------------------------------------------------
// private members
//---------------------------------------------------
private:
struct SoundSymbol
{
F32 mWaveExpansion [ NUM_VOICE_SYMBOL_WAVES ];
bool mWaveActive [ NUM_VOICE_SYMBOL_WAVES ];
F64 mWaveFadeOutStartTime [ NUM_VOICE_SYMBOL_WAVES ];
F32 mWaveOpacity [ NUM_VOICE_SYMBOL_WAVES ];
LLPointer<LLImageGL> mTexture [ NUM_VOICE_SYMBOL_WAVES ];
bool mActive;
LLVector3 mPosition;
};
LLFrameTimer mTimer; // so I can ask the current time in seconds
F64 mCurrentTime; // current time in seconds, captured every step
F64 mPreviousTime; // copy of "current time" from last frame
SoundSymbol mSoundSymbol; // the sound symbol that appears over the avatar's head
bool mVoiceEnabled; // if off, no rendering should happen
bool mCurrentlySpeaking; // is the user currently speaking?
LLVector3 mVoiceSourceWorldPosition; // give this to me every step - I need it to update the sound symbol
F32 mSpeakingAmplitude; // this should be set as often as possible when the user is speaking
F32 mMaxGesticulationAmplitude; // this is the upper-limit of the envelope of detectable gesticulation leves
F32 mMinGesticulationAmplitude; // this is the lower-limit of the envelope of detectable gesticulation leves
};//-----------------------------------------------------------------
// end of LLVoiceVisualizer class
//------------------------------------------------------------------
#endif //LL_VOICE_VISUALIZER_H
|
