def selfdetection(self, inputtier1):
"""
Self-Repetition detection.
@param inputtier1 (Tier)
"""
# Verifications: is there any data?
if inputtier1.IsEmpty() is True:
raise Exception("Repetition. Empty input tokens tier.\n")
# Update the stoplist
if self._use_stopwords is True:
stpw = self.relevancy( inputtier1 )
else:
stpw = self.stopwords
# Create repeat objects
repeatobj = Repetitions( )
# Create output data
srctier = Tier("Sources")
reptier = Tier("Repetitions")
nbrepeats = 1
# Initialization of tokstart and tokend
tokstart = 0
if inputtier1[0].GetLabel().IsDummy():
tokstart = 1
toksearch = self.find_next_break( inputtier1, tokstart+1 , empan=1)
tokend = self.find_next_break( inputtier1, tokstart+1 , empan=self._empan)
# Detection is here:
while tokstart < tokend:
# Build an array with the tokens
tokens1 = list()
for i in range(tokstart, tokend+1):
tokens1.append( inputtier1[i].GetLabel().GetValue() )
speaker1 = DataSpeaker( tokens1, stpw )
# Detect repeats in these data
repeatobj.detect( speaker1, toksearch-tokstart, None )
# Save repeats
if repeatobj.get_repeats_size()>0:
n = self._addrepetition(repeatobj, nbrepeats, inputtier1, inputtier1, tokstart, tokstart, srctier, reptier)
nbrepeats = nbrepeats + n
# Prepare next search
tokstart = toksearch
toksearch = self.find_next_break( inputtier1 , tokstart+1 , empan=1 )
tokend = self.find_next_break( inputtier1 , tokstart+1 , empan=self._empan )
return (srctier,reptier)
def otherdetection(self, inputtier1, inputtier2):
"""
Other-Repetition detection.
@param inputtier (Tier)
"""
# Verifications: is there any data?
if inputtier1.IsEmpty() is True:
raise Exception("Repetition. Empty input tokens tier.\n")
# Update the stoplist
if self._use_stopwords is True:
# other-repetition: relevance of the echoing-speaker
stpw = self.relevancy( inputtier2 )
else:
stpw = self.stopwords
# Create repeat objects
repeatobj = Repetitions( )
# Create output data
srctier = Tier("OR-Source")
reptier = Tier("OR-Repetition")
nbrepeats = 1
# Initialization of tokstart, and tokend
tokstartsrc = 0
if inputtier1[0].GetLabel().IsDummy():
tokstartsrc = 1
tokendsrc = min(20, inputtier1.GetSize()-1)
# Detection is here:
# detect() is applied work by word, from tokstart to tokend
while tokstartsrc < tokendsrc:
# Build an array with the tokens
tokens1 = list()
for i in range(tokstartsrc, tokendsrc):
tokens1.append( inputtier1[i].GetLabel().GetValue() )
speaker1 = DataSpeaker( tokens1, stpw )
# Create speaker2
tokens2 = list()
nbbreaks = 0
tokstartrep = -1
a = inputtier1[tokstartsrc]
for (r,b) in enumerate(inputtier2):
if b.GetLocation().GetBeginMidpoint() >= a.GetLocation().GetBeginMidpoint():
if tokstartrep == -1:
tokstartrep = r
if b.GetLabel().IsSilence():
nbbreaks = nbbreaks + 1
if nbbreaks == self._empan:
break
tokens2.append( b.GetLabel().GetValue() )
speaker2 = DataSpeaker( tokens2, stpw )
if DEBUG is True:
print "SRC : ",speaker1
print "ECHO: ",speaker2
# Detect repeats in these data: search if the first token of spk1
# is the first token of a source.
repeatobj.detect( speaker1, 1, speaker2 )
# Save repeats
shift = 1
if repeatobj.get_repeats_size()>0:
if DEBUG is True:
print " ----> found : "
repeatobj.get_repeat(0).print_echo()
s,e = repeatobj.get_repeat_source(0)
n = self._addrepetition(repeatobj, nbrepeats, inputtier1, inputtier2, tokstartsrc, tokstartrep, srctier, reptier)
if n > 0:
nbrepeats = nbrepeats + n
shift = e + 1
while speaker1.is_token(speaker1.get_token(shift)) is False and shift < 20:
shift = shift + 1
tokstartsrc = tokstartsrc + shift
tokstartsrc = min(tokstartsrc, inputtier1.GetSize()-1)
tokendsrc = min(tokstartsrc + 20, inputtier1.GetSize()-1)
return (srctier,reptier)
