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
|
/*
* Copyright 2017 The TensorFlow Authors. All Rights Reserved.
*
* 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.
*/
package org.tensorflow.demo;
import android.util.Log;
import android.util.Pair;
import java.util.ArrayDeque;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.Deque;
import java.util.List;
/** Reads in results from an instantaneous audio recognition model and smoothes them over time. */
public class RecognizeCommands {
// Configuration settings.
private List<String> labels = new ArrayList<String>();
private long averageWindowDurationMs;
private float detectionThreshold;
private int suppressionMs;
private int minimumCount;
private long minimumTimeBetweenSamplesMs;
// Working variables.
private Deque<Pair<Long, float[]>> previousResults = new ArrayDeque<Pair<Long, float[]>>();
private String previousTopLabel;
private int labelsCount;
private long previousTopLabelTime;
private float previousTopLabelScore;
private static final String SILENCE_LABEL = "_silence_";
private static final long MINIMUM_TIME_FRACTION = 4;
public RecognizeCommands(
List<String> inLabels,
long inAverageWindowDurationMs,
float inDetectionThreshold,
int inSuppressionMS,
int inMinimumCount,
long inMinimumTimeBetweenSamplesMS) {
labels = inLabels;
averageWindowDurationMs = inAverageWindowDurationMs;
detectionThreshold = inDetectionThreshold;
suppressionMs = inSuppressionMS;
minimumCount = inMinimumCount;
labelsCount = inLabels.size();
previousTopLabel = SILENCE_LABEL;
previousTopLabelTime = Long.MIN_VALUE;
previousTopLabelScore = 0.0f;
minimumTimeBetweenSamplesMs = inMinimumTimeBetweenSamplesMS;
}
/** Holds information about what's been recognized. */
public static class RecognitionResult {
public final String foundCommand;
public final float score;
public final boolean isNewCommand;
public RecognitionResult(String inFoundCommand, float inScore, boolean inIsNewCommand) {
foundCommand = inFoundCommand;
score = inScore;
isNewCommand = inIsNewCommand;
}
}
private static class ScoreForSorting implements Comparable<ScoreForSorting> {
public final float score;
public final int index;
public ScoreForSorting(float inScore, int inIndex) {
score = inScore;
index = inIndex;
}
@Override
public int compareTo(ScoreForSorting other) {
if (this.score > other.score) {
return -1;
} else if (this.score < other.score) {
return 1;
} else {
return 0;
}
}
}
public RecognitionResult processLatestResults(float[] currentResults, long currentTimeMS) {
if (currentResults.length != labelsCount) {
throw new RuntimeException(
"The results for recognition should contain "
+ labelsCount
+ " elements, but there are "
+ currentResults.length);
}
if ((!previousResults.isEmpty()) && (currentTimeMS < previousResults.getFirst().first)) {
throw new RuntimeException(
"You must feed results in increasing time order, but received a timestamp of "
+ currentTimeMS
+ " that was earlier than the previous one of "
+ previousResults.getFirst().first);
}
final int howManyResults = previousResults.size();
// Ignore any results that are coming in too frequently.
if (howManyResults > 1) {
final long timeSinceMostRecent = currentTimeMS - previousResults.getLast().first;
if (timeSinceMostRecent < minimumTimeBetweenSamplesMs) {
return new RecognitionResult(previousTopLabel, previousTopLabelScore, false);
}
}
// Add the latest results to the head of the queue.
previousResults.addLast(new Pair<Long, float[]>(currentTimeMS, currentResults));
// Prune any earlier results that are too old for the averaging window.
final long timeLimit = currentTimeMS - averageWindowDurationMs;
while (previousResults.getFirst().first < timeLimit) {
previousResults.removeFirst();
}
// If there are too few results, assume the result will be unreliable and
// bail.
final long earliestTime = previousResults.getFirst().first;
final long samplesDuration = currentTimeMS - earliestTime;
if ((howManyResults < minimumCount)
|| (samplesDuration < (averageWindowDurationMs / MINIMUM_TIME_FRACTION))) {
Log.v("RecognizeResult", "Too few results");
return new RecognitionResult(previousTopLabel, 0.0f, false);
}
// Calculate the average score across all the results in the window.
float[] averageScores = new float[labelsCount];
for (Pair<Long, float[]> previousResult : previousResults) {
final float[] scoresTensor = previousResult.second;
int i = 0;
while (i < scoresTensor.length) {
averageScores[i] += scoresTensor[i] / howManyResults;
++i;
}
}
// Sort the averaged results in descending score order.
ScoreForSorting[] sortedAverageScores = new ScoreForSorting[labelsCount];
for (int i = 0; i < labelsCount; ++i) {
sortedAverageScores[i] = new ScoreForSorting(averageScores[i], i);
}
Arrays.sort(sortedAverageScores);
// See if the latest top score is enough to trigger a detection.
final int currentTopIndex = sortedAverageScores[0].index;
final String currentTopLabel = labels.get(currentTopIndex);
final float currentTopScore = sortedAverageScores[0].score;
// If we've recently had another label trigger, assume one that occurs too
// soon afterwards is a bad result.
long timeSinceLastTop;
if (previousTopLabel.equals(SILENCE_LABEL) || (previousTopLabelTime == Long.MIN_VALUE)) {
timeSinceLastTop = Long.MAX_VALUE;
} else {
timeSinceLastTop = currentTimeMS - previousTopLabelTime;
}
boolean isNewCommand;
if ((currentTopScore > detectionThreshold) && (timeSinceLastTop > suppressionMs)) {
previousTopLabel = currentTopLabel;
previousTopLabelTime = currentTimeMS;
previousTopLabelScore = currentTopScore;
isNewCommand = true;
} else {
isNewCommand = false;
}
return new RecognitionResult(currentTopLabel, currentTopScore, isNewCommand);
}
}
|
