speech segmentation 0.0029244600000000003
topic segmentation 0.00290433
segmentation algorithm 0.0024983310000000003
speech data 0.00227267
text segmentation 0.0022347310000000002
acoustic speech 0.002199804
segmentation methods 0.002070436
segmentation systems 0.0020592550000000003
unsupervised segmentation 0.002056936
segmentation baseline 0.002031897
baseline segmentation 0.002031897
segmentation algorithms 0.002022935
speech segments 0.002011644
acoustic data 0.002009174
segmentation approaches 0.002002026
reference segmentation 0.001997673
segmentation com 0.001968468
segmentation accuracy 0.00195477
segmentation algo 0.0019397540000000001
reliable segmentation 0.00192304
segmentation perspec 0.0019210590000000001
segmentation granularity 0.0019196340000000001
segment speech 0.0018291639999999999
acoustic similarity 0.001802257
audio data 0.001787097
multiple speech 0.0017492179999999999
topic structure 0.001725596
topic analysis 0.0017057650000000001
topic seg 0.001696623
speech document 0.0016937929999999999
segmentation 0.00169281
processing speech 0.0016686779999999998
speech processing 0.0016686779999999998
speech documents 0.0016664429999999999
topic boundaries 0.001664765
many word 0.001652527
similar speech 0.001638367
such data 0.0015941829999999999
speech signal 0.001581788
topic changes 0.001577866
unsupervised topic 0.001575646
word boundaries 0.0015722650000000002
acoustic features 0.0015622560000000001
speech transcript 0.001550356
word error 0.001532729
word boundary 0.001532191
audio segments 0.001526071
speech process 0.0015120889999999999
speech input 0.001510345
acoustic matrix 0.0015049680000000002
topic segmen 0.001501388
speech recognizer 0.001497596
language model 0.001497535
robust topic 0.001494857
continuous speech 0.001492996
high word 0.001479526
acoustic information 0.001470399
speech sig 0.00146653
word sequences 0.0014374460000000002
word statistics 0.001423996
word paths 0.00141748
unique word 0.001387151
word dis 0.001380993
similarity matrix 0.0013709170000000001
word type 0.0013657230000000001
word fragment 0.00134646
high acoustic 0.0013286600000000002
acoustic signal 0.001318292
acoustic matching 0.0013075130000000002
acoustic sequences 0.00128658
acoustic matches 0.001285326
data our 0.0012793309999999999
acoustic comparison 0.001275309
acoustic patterns 0.0012750370000000001
acoustic alignments 0.001258694
acoustic stream 0.001258205
recognition performance 0.0012478699999999999
acoustic input 0.001246849
acoustic com 0.001243812
acoustic cues 0.001234286
speech 0.00123165
topic 0.00121152
acoustic waveform 0.001210587
alignment algorithm 0.001198822
acoustic pat 0.001195239
similar segments 0.001186711
similarity change 0.001176164
unsupervised algorithm 0.001169647
discourse structure 0.0011523990000000001
lexical distribution 0.001143385
discourse analysis 0.001132568
same speaker 0.0011287760000000002
same time 0.001118714
lexical cohesion 0.001104184
content words 0.001095506
similar performance 0.0010917029999999999
other system 0.001086627
warping algorithm 0.0010862369999999999
block similarity 0.00107795
internal similarity 0.00106661
