segment.cpp
10.4 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
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
/*
* 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 a segment.
* A segment is a list of Token.
*/
#include "segment.h" // class's header file
#include "speech.h"
#include "speechset.h"
Logger* Segment::logger = Logger::getLogger();
Segment* Segment::CreateWithDuration(const int& _startTime, const int& _duration, Speech* parent)
{
Segment* segment = new Segment();
segment->speech = parent;
return (Segment*) segment->InitWithDuration(_startTime, _duration);
}
Segment* Segment::CreateWithEndTime(const int& _startTime, const int& _endTime, Speech* parent)
{
Segment* segment = new Segment();
segment->speech = parent;
return (Segment*) segment->InitWithEndTime(_startTime, _endTime);
}
bool Segment::AreStartTimeAndEndTimeValid(const int& _startTime, const int& _endTime)
{
if(!TimedObject::AreStartTimeAndEndTimeValid(_startTime, _endTime))
return false;
return _startTime <= GetLowestTokenStartTime() && _endTime >= GetHighestTokenEndTime();
}
/**
* Merge all Segments in one segments
*/
Segment* Segment::Merge(const vector<Segment*> & segments)
{
int start=INT_MAX, end=0;
Token* t_start = NULL;
Token* t_end = NULL;
Segment* currentSegment = NULL;
for (size_t i=0 ; i < segments.size() ; ++i)
{
currentSegment = segments[i];
if (currentSegment->GetStartTime() < start)
{
t_start = currentSegment->f_token;
start = currentSegment->GetStartTime();
}
if (currentSegment->GetEndTime() > end)
{
t_end = currentSegment->l_token;
end = currentSegment->GetEndTime();
}
}
Segment* seg = Segment::CreateWithEndTime(start, end, currentSegment->GetParentSpeech());
seg->f_token = t_start;
seg->l_token = t_end;
return seg;
}
int Segment::GetLowestTokenStartTime()
{
int lowestStartTime = 0;
for(size_t i = 0; i < f_token->GetNbOfNextTokens() ; ++i)
{
int sTime = f_token->GetNextToken(i)->GetStartTime();
if(sTime < lowestStartTime)
lowestStartTime = sTime;
}
return lowestStartTime;
}
int Segment::GetHighestTokenEndTime()
{
int highestEndTime = 0;
for(size_t i = 0; i < l_token->GetNbOfNextTokens() ; ++i)
{
int eTime = l_token->GetNextToken(i)->GetEndTime();
if(eTime < highestEndTime)
highestEndTime = eTime;
}
return highestEndTime;
}
// class constructor
Segment::Segment()
{
//f_token = new Token();
f_token = Token::CreateWithEndTime(0, 0, this);
l_token = Token::CreateWithEndTime(0, 0, this);
ignoreSegmentInScoring = false;
}
// class destructor
Segment::~Segment()
{
vector<Token*> listAllTokens = ToTopologicalOrderedStruct();
for(size_t i=0; i<listAllTokens.size(); ++i)
{
Token* ptr_elt = listAllTokens[i];
if(ptr_elt)
delete ptr_elt;
}
listAllTokens.clear();
delete f_token;
delete l_token;
}
string Segment::ToString()
{
std::ostringstream oss;
oss << "<Segment " << TimedObject::ToString() << ">\n\tspkrId='" << GetSpeakerId()
<< "' src='" << GetSource() << "' chnl='" << GetChannel() << "'" << endl;
vector<Token*> tokens = ToTopologicalOrderedStruct();
Token* token;
for(size_t i = 0; i < tokens.size(); ++i)
{
token = tokens[i];
if(token != NULL)
oss << "\t" << token->ToString() << endl;
}
oss << "</Segment>";
return oss.str();
}
string Segment::ToStringAsLine()
{
std::ostringstream oss;
oss << "<Segment " << TimedObject::ToString() << " spkrId='" << GetSpeakerId()
<< "' src='" << GetSource() << "' chnl='" << GetChannel() << "'";
vector<Token*> tokens = ToTopologicalOrderedStruct();
Token* token;
for(size_t i = 0; i < tokens.size(); ++i)
{
token = tokens[i];
if(token != NULL)
oss << " " << token->ToString();
}
return oss.str();
}
// sets the value of token
void Segment::AddFirstToken(Token* token)
{
if (token->GetStartTime() != -1 && (token->GetStartTime() < this->GetStartTime()))
{
char buffer[BUFFER_SIZE];
sprintf(buffer, "Segment: Tried to add a token with start time before begin of segment file ='%s' tkn='%s' src=%s chnl=%s st=%d et=%d seg: st=%d et=%d",
GetParentSpeech()->GetParentSpeechSet()->GetSourceFileName().c_str(),
token->GetText().c_str(), GetSource().c_str(), GetChannel().c_str(), token->GetStartTime(), token->GetEndTime(), GetStartTime(), GetEndTime());
LOG_FATAL(logger, buffer);
exit(E_INVALID);
}
else
{
f_token->AddNextToken(token);
}
}
// sets the value of token
void Segment::AddLastToken(Token* token)
{
if (token->GetEndTime() != -1 && (token->GetEndTime() > this->GetEndTime()))
{
char buffer[BUFFER_SIZE];
sprintf(buffer, "Segment: Tried to add a token with start time before begin of segment file ='%s' tkn='%s' src=%s chnl=%s st=%d et=%d seg: st=%d et=%d",
GetParentSpeech()->GetParentSpeechSet()->GetSourceFileName().c_str(),
token->GetText().c_str(), GetSource().c_str(), GetChannel().c_str(), token->GetStartTime(), token->GetEndTime(), GetStartTime(), GetEndTime());
LOG_FATAL(logger, buffer);
exit(E_INVALID);
}
else
{
l_token->AddNextToken(token);
}
}
/**
* Output a plan version of the segment.
* Put them on a topological order.
*/
vector<Token*> Segment::ToTopologicalOrderedStruct()
{
vector<Token*> res;
for(size_t i = 0 ; i < f_token->GetNbOfNextTokens() ; ++i)
{
Token* token = f_token->GetNextToken(i);
res.push_back(token);
ToTopologicalOrderedStruct(token, &res);
}
return res;
}
/**
* Recurs methods to compute a topological order of a graph
*/
void Segment::ToTopologicalOrderedStruct(Token* start, vector<Token*>* doneNode)
{
if (!isLastToken(start))
{
for(size_t i = 0 ; i < start->GetNbOfNextTokens() ; ++i)
{
Token* token = start->GetNextToken(i);
if (find(doneNode->begin(), doneNode->end(), token) == doneNode->end())
{
doneNode->push_back(token);
ToTopologicalOrderedStruct(token, doneNode);
}
}
}
}
/**
* Return if the token is on the list of the First tokens.
*/
bool Segment::isFirstToken(Token* token)
{
for(size_t i = 0 ; i < f_token->GetNbOfNextTokens() ; ++i)
if (f_token->GetNextToken(i) == token)
return true;
return false;
}
/**
* Return if the token is on the list of the last tokens.
*/
bool Segment::isLastToken(Token* token)
{
for(size_t i = 0 ; i < l_token->GetNbOfNextTokens() ; ++i)
if (l_token->GetNextToken(i) == token)
return true;
return false;
}
/**
* Return the parent Speech
*/
Speech* Segment::GetParentSpeech()
{
return speech;
}
/** Determines if case is taken into account to align Tokens part of this Speech. */
bool Segment::PerformCaseSensitiveAlignment()
{
return speech->PerformCaseSensitiveAlignment();
}
/** Determines if fragments are considered as correct when aligning Tokens part of this Speech. */
bool Segment::AreFragmentsCorrect()
{
return speech->AreFragmentsCorrect();
}
/** Determines if optionally deletable Tokens need to be accounted for. */
bool Segment::UseOptionallyDeletable()
{
return speech->UseOptionallyDeletable();
}
/** Replaces the token with a linked list of tokens. The initial token is NOT deleted **/
void Segment:: ReplaceTokenWith(Token *token, const vector<Token*> & startTokens, const vector<Token*> & endTokens)
{
// Store a list of prev tokens to avoid continual adding of tokens!!!
vector<Token *>prevTokens;
for (size_t p=0; p<token->GetNbOfPrecTokens(); ++p)
prevTokens.push_back(token->GetPrecToken(p));
// Do the link
for (size_t s = 0; s<startTokens.size(); ++s)
for (size_t p=0; p<prevTokens.size(); ++p)
prevTokens[p]->LinkTokens(startTokens[s]);
// Link in the Starts
if (isFirstToken(token))
for (size_t s = 0; s<startTokens.size(); ++s)
AddFirstToken(startTokens[s]);
// Store a list of next tokens to avoid continual adding of tokens!!!
vector<Token *>nextTokens;
for (size_t n=0; n<token->GetNbOfNextTokens(); ++n)
nextTokens.push_back(token->GetNextToken(n));
// Do the link
for (size_t e = 0; e<endTokens.size(); ++e)
for (size_t n=0; n<nextTokens.size(); ++n)
endTokens[e]->LinkTokens(nextTokens[n]);
// Link in the End
if (isLastToken(token))
for (size_t e = 0; e<endTokens.size(); ++e)
AddLastToken(endTokens[e]);
// Unlink the token --- With the assumption that something has replaced IT
if (isFirstToken(token))
f_token->UnlinkNextToken(token);
if(isLastToken(token))
l_token->UnlinkNextToken(token);
while(token->GetNbOfPrecTokens() > 0)
token->GetPrecToken(0)->UnlinkTokens(token);
while(token->GetNbOfNextTokens() > 0)
token->UnlinkTokens(token->GetNextToken(0));
// cleanup
prevTokens.clear();
nextTokens.clear();
}
int Segment::GetMinTokensTime()
{
int minTime = -1;
vector<Token*> vectok = ToTopologicalOrderedStruct();
for(size_t veci=0; veci<vectok.size(); ++veci)
if( (minTime == -1) || (vectok[veci]->GetStartTime() < minTime) )
minTime = vectok[veci]->GetStartTime();
vectok.clear();
return minTime;
}
int Segment::GetMaxTokensTime()
{
int maxTime = -1;
vector<Token*> vectok = ToTopologicalOrderedStruct();
for(size_t veci=0; veci<vectok.size(); ++veci)
if( (maxTime == -1) || (vectok[veci]->GetEndTime() > maxTime) )
maxTime = vectok[veci]->GetStartTime();
vectok.clear();
return maxTime;
}
void Segment::SetTokensOptionallyDeletable()
{
vector<Token*> vectok = ToTopologicalOrderedStruct();
for(size_t veci=0; veci<vectok.size(); ++veci)
{
vectok[veci]->BecomeOptionallyDeletable();
}
vectok.clear();
}