translation system 0.00333225
language models 0.0028809829999999997
different word 0.0028311
language sentences 0.0026206349999999996
translation models 0.002608403
input language 0.002575418
asr system 0.002556975
speech recognition 0.002553923
language processing 0.002548331
output language 0.0024850709999999997
language modeling 0.002481883
natural language 0.002464324
based language 0.0024510139999999996
language selection 0.00243314
language pairs 0.0024242369999999997
training speech 0.002412639
automatic speech 0.002410637
native language 0.0023799959999999997
language pair 0.002369366
language barriers 0.002353723
language barrier 0.002353723
speech synthesis 0.00233942
output speech 0.002282291
unsupervised speech 0.0022431309999999998
word forms 0.002220214
speech sound 0.002203148
continuous speech 0.002186344
based translation 0.002178434
robust speech 0.002171569
annotated speech 0.002164272
tts system 0.002163803
speech samples 0.00216368
thetic speech 0.002152689
matic speech 0.002152689
translation demo 0.002117986
bile translation 0.002094752
chine translation 0.002082091
language 0.00202961
voice model 0.001891266
adaptation data 0.001839133
asr models 0.0018331279999999998
speech 0.00182683
translation 0.00175703
model trans 0.001684488
speaker adaptation 0.0016428279999999998
vocabulary asr 0.001633677
average model 0.00163108
model transformations 0.001623707
markov model 0.001584422
system 0.00157522
voice adaptation 0.001559881
training data 0.0015493669999999998
voice models 0.0015356789999999999
new voice 0.0015290529999999998
asr systems 0.001503419
baseline asr 0.001486508
other user 0.001466743
tts adaptation 0.0014641580000000001
new results 0.001438247
standard asr 0.001433111
asr corpora 0.0014271969999999998
other languages 0.001382401
finnish asr 0.001346547
guage asr 0.001346135
new voices 0.00133757
adaptation methods 0.001319574
ploy asr 0.0013062
fast adaptation 0.00130223
adaptation transformations 0.001292322
unsupervised adaptation 0.001291876
new methods 0.001288746
large vocabulary 0.001279327
target speaker 0.001263152
monolingual adaptation 0.001247692
sufficient models 0.001241921
input voice 0.001230114
pervised adaptation 0.001218262
lingual adaptation 0.001213418
adaptation samples 0.001212425
model 0.00120696
supervised adaptation 0.001199712
average speaker 0.001191373
many voices 0.001190047
target voice 0.001180205
high quality 0.0011514960000000001
speaker adap 0.001143418
output voice 0.0011397669999999999
original speaker 0.0011376329999999999
standard voice 0.001135662
many features 0.001134772
single speaker 0.001125718
own voice 0.001121235
nlp research 0.001115411
first results 0.001110938
tts systems 0.001110247
average voice 0.001108426
figure speaker 0.001108182
lingual speaker 0.0011050959999999999
speaker adapta 0.001099641
nal speaker 0.001094047
