speech.cpp
5.95 KB
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
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
/*
* ASCLITE
* Author: Jerome Ajot, Jon Fiscus, Nicolas Radde, Chris Laprun
*
* This software was developed at the National Institute of Standards and Technology by
* employees of the Federal Government in the course of their official duties. Pursuant
* to title 17 Section 105 of the United States Code this software is not subject to
* copyright protection and is in the public domain. ASCLITE is an experimental system.
* NIST assumes no responsibility whatsoever for its use by other parties, and makes no
* guarantees, expressed or implied, about its quality, reliability, or any other
* characteristic. We would appreciate acknowledgement if the software is used.
*
* THIS SOFTWARE IS PROVIDED "AS IS." With regard to this software, NIST MAKES NO EXPRESS
* OR IMPLIED WARRANTY AS TO ANY MATTER WHATSOEVER, INCLUDING MERCHANTABILITY,
* OR FITNESS FOR A PARTICULAR PURPOSE.
*/
/**
* Internal representation of an hypothesis file or a reference file.
*/
#include "speech.h" // class's header file
#include "speechset.h"
Logger* Speech::m_pLogger = Logger::getLogger();
// class constructor
Speech::Speech() {}
// class constructor
Speech::Speech(SpeechSet* parent)
{
parentSet = parent;
}
Speech::Speech(const vector<Segment *>& segments)
{
m_segments = vector<Segment *>(segments);
}
// class destructor
Speech::~Speech()
{
for(size_t i=0; i<m_segments.size(); ++i)
{
Segment* ptr_elt = m_segments[i];
if(ptr_elt)
delete ptr_elt;
}
m_segments.clear();
}
bool Speech::PerformCaseSensitiveAlignment()
{
return parentSet->PerformCaseSensitiveAlignment();
}
bool Speech::AreFragmentsCorrect()
{
return parentSet->AreFragmentsCorrect();
}
bool Speech::UseOptionallyDeletable()
{
return parentSet->UseOptionallyDeletable();
}
/**
* Retrieves the SpeechSet in which this Speech is located
*/
SpeechSet* Speech::GetParentSpeechSet()
{
return parentSet;
}
/**
* Return the next Segment starting at the specified time for
* the specified source and channel. If the time is in the middle of
* A segment return the segment itself.
*/
Segment* Speech::NextSegment(const int& time, const string& source, const string& channel)
{
int last_endTime = 0;
for (size_t i=0 ; i < m_segments.size() ; ++i)
{
Segment *currentSegment = m_segments[i];
if (currentSegment->GetSource() == source && currentSegment->GetChannel() == channel)
{
if (currentSegment->GetEndTime() > time && last_endTime <= time)
{
return currentSegment;
}
last_endTime = currentSegment->GetEndTime();
}
}
return NULL;
}
/**
* Return the segments of this speech by the given time
*/
vector<Segment*> Speech::GetSegmentsByTime(const int& start, const int& end, const string& source, const string& channel)
{
vector<Segment*> res;
for (size_t i=0 ; i < m_segments.size() ; ++i)
{
Segment *currentSegment = m_segments[i];
if (currentSegment->GetSource() == source && currentSegment->GetChannel() == channel)
{
int s_mid = ((currentSegment->GetEndTime()+currentSegment->GetStartTime()) / 2);
if (s_mid >= start && s_mid < end)
{
res.push_back(currentSegment);
}
}
}
return res;
}
string Speech::ToString()
{
std::ostringstream oss;
oss << "<Speech NbOfSegments='" << NbOfSegments() << "'>";
for(size_t i = 0; i < NbOfSegments(); ++i)
{
Segment *seg = GetSegment(i);
oss << seg->ToString() << endl;
}
oss << "</Speech>";
return oss.str();
}
void Speech::RemoveSegment(Segment* currentSegment)
{
list<Token*> listPreviousTokenofFirstToken;
list<Token*> listNextTokenofLastToken;
// Remove links from the previous tokens of the first tokens of the segment
for(size_t f=0; f<currentSegment->GetNumberOfFirstToken(); ++f)
{
Token* firstToken = currentSegment->GetFirstToken(f);
if(firstToken)
{
for(size_t p=0; p<firstToken->GetNbOfPrecTokens(); ++p)
{
Token* previousTokenofFirstToken = firstToken->GetPrecToken(p);
listPreviousTokenofFirstToken.push_back(previousTokenofFirstToken);
previousTokenofFirstToken->UnlinkNextToken(firstToken);
}
}
}
// Remove links from the next tokens of the last tokens of the segment
for(size_t l=0; l<currentSegment->GetNumberOfLastToken(); ++l)
{
Token* lastToken = currentSegment->GetLastToken(l);
if(lastToken)
{
for(size_t n=0; n<lastToken->GetNbOfNextTokens(); ++n)
{
Token* nextTokenofLastToken = lastToken->GetNextToken(n);
listNextTokenofLastToken.push_back(nextTokenofLastToken);
nextTokenofLastToken->UnlinkPrevToken(lastToken);
}
}
}
// Re-attach the tokens
list<Token*>::iterator prev = listPreviousTokenofFirstToken.begin();
list<Token*>::iterator eprev = listPreviousTokenofFirstToken.end();
list<Token*>::iterator next = listNextTokenofLastToken.begin();
list<Token*>::iterator enext = listNextTokenofLastToken.end();
while(prev != eprev)
{
while(next != enext)
{
(*prev)->AddNextToken(*next);
(*next)->AddPrecToken(*prev);
++next;
}
++prev;
}
listPreviousTokenofFirstToken.clear();
listNextTokenofLastToken.clear();
// Remove Segment from vector
vector<Segment*>::iterator SegIter = m_segments.begin();
while (SegIter != m_segments.end() && (*SegIter) != currentSegment)
++SegIter;
if (SegIter == m_segments.end())
{
LOG_FATAL(m_pLogger, "Speech::RemoveSegment(), the segment is not at the right spot!!");
exit(E_INVALID);
}
m_segments.erase(SegIter);
// destroy! the segment now
delete currentSegment;
}
int Speech::GetMinTokensTime()
{
int MinTime = -1;
for(size_t spj=0; spj<NbOfSegments(); ++spj)
{
int tmpmin = GetSegment(spj)->GetMinTokensTime();
if ( (MinTime == -1) || (tmpmin < MinTime) )
MinTime = tmpmin;
}
return MinTime;
}
int Speech::GetMaxTokensTime()
{
int MaxTime = -1;
for(size_t spj=0; spj<NbOfSegments(); ++spj)
{
int tmpmax = GetSegment(spj)->GetMaxTokensTime();
if ( (MaxTime == -1) || (tmpmax > MaxTime) )
MaxTime = tmpmax;
}
return MaxTime;
}