speech data 0.002937703
data set 0.0028208749999999996
test data 0.0028071
training data 0.0027222049999999997
development data 0.002563737
data sets 0.0025168449999999998
evaluation data 0.002479398
ment data 0.002439397
switchboard data 0.0024253229999999996
tuning data 0.0024201459999999998
data collection 0.002406177
velopment data 0.0024007169999999997
opment data 0.0023994389999999997
data stream 0.0023994389999999997
single word 0.0019130010000000001
manual word 0.001821549
automatic word 0.001783898
word transcript 0.001769538
vocabulary word 0.001766925
word trigram 0.001753662
word transcripts 0.001740381
word recognizer 0.001728691
word bigram 0.001726893
word unigram 0.001711221
clustering method 0.001471909
clustering algorithm 0.001429006
clustering results 0.0014247309999999998
words representation 0.001420515
clustering performance 0.001392923
same speech 0.00136855
long words 0.0013534649999999999
acoustic model 0.001306692
same cluster 0.001288953
feature set 0.001284185
learning algorithm 0.001268879
tual words 0.001268869
ognized words 0.001268869
meaningful words 0.001268869
speech corpus 0.001235826
topic clustering 0.001205967
similar clustering 0.0011928
space model 0.001190292
training algorithm 0.001181409
several clustering 0.001165993
clustering methods 0.001164866
document clustering 0.001135119
clustering experiments 0.0011332529999999999
speech corpora 0.001133051
phone speech 0.00111119
target language 0.001110881
classification algorithm 0.00110651
language processing 0.001103024
clustering labels 0.001092081
resource language 0.001087205
clustering conversations 0.001086366
online learning 0.001073586
different classifier 0.001073065
similar results 0.001072187
speech processing 0.001071549
words 0.00106496
same topic 0.001061272
graph clustering 0.001058165
resource speech 0.00105573
cluster similarity 0.0010555999999999999
optimal clustering 0.001051488
clustering algorithms 0.001039336
speech process 0.00103918
speech recognition 0.001038448
natural language 0.001029228
selection method 0.001028257
bisection clustering 0.001027949
automatic speech 0.0010239609999999999
algorithm development 0.0010229409999999999
unsupervised clustering 0.001022614
speech input 0.001021301
supervised learning 0.0010178230000000002
various set 0.001004415
language switchboard 0.001000241
same phone 9.98594E-4
ful clustering 9.97883E-4
phone set 9.94362E-4
reference language 9.92613E-4
clustering meth 9.88409E-4
entire clustering 9.86837E-4
ing performance 9.82845E-4
speech intervals 9.82749E-4
ral language 9.81562E-4
language phoneme 9.79969E-4
noisy method 9.77044E-4
clustering configuration 9.76888E-4
speech activity 9.763700000000001E-4
speech sig 9.76181E-4
agglomerative clustering 9.761069999999999E-4
clustering library 9.75496E-4
cluto clustering 9.75496E-4
cation language 9.750480000000001E-4
same target 9.6681E-4
term results 9.656999999999999E-4
gle speech 9.6089E-4
telephone speech 9.5721E-4
