David Imseng
David Imseng
Verifierad e-postadress på idiap.ch - Startsida
TitelCiteras avÅr
Multilingual deep neural network based acoustic modeling for rapid language adaptation
NT Vu, D Imseng, D Povey, P Motlicek, T Schultz, H Bourlard
2014 IEEE international conference on acoustics, speech and signal …, 2014
782014
Tuning-robust initialization methods for speaker diarization
D Imseng, G Friedland
IEEE Transactions on Audio, Speech, and Language Processing 18 (8), 2028-2037, 2010
472010
The ICSI RT-09 speaker diarization system
G Friedland, A Janin, D Imseng, X Anguera, L Gottlieb, M Huijbregts, ...
IEEE Transactions on Audio, Speech, and Language Processing 20 (2), 371-381, 2011
462011
Using out-of-language data to improve an under-resourced speech recognizer
D Imseng, P Motlicek, H Bourlard, PN Garner
Speech communication 56, 142-151, 2014
392014
Using KL-divergence and multilingual information to improve ASR for under-resourced languages
D Imseng, H Bourlard, PN Garner
2012 IEEE International Conference on Acoustics, Speech and Signal …, 2012
382012
Comparing different acoustic modeling techniques for multilingual boosting
D Imseng, J Dines, P Motlicek, PN Garner, H Bourlard
Proceedings of Interspeech, 2012
332012
Fast and flexible Kullback-Leibler divergence based acoustic modeling for non-native speech recognition
D Imseng, R Rasipuram, MM Doss
322011
Current trends in multilingual speech processing
H Bourlard, J Dines, M Magimai-Doss, PN Garner, D Imseng, P Motlicek, ...
Sadhana 36 (5), 885-915, 2011
252011
Leveraging speaker diarization for meeting recognition from distant microphones
A Stolcke, G Friedland, D Imseng
2010 IEEE International Conference on Acoustics, Speech and Signal …, 2010
252010
Towards mixed language speech recognition systems
D Imseng, H Bourlard, M Magimai Doss
Proc. of Interspeech, 278-281, 2010
252010
Robust speaker diarization for short speech recordings
D Imseng, G Friedland
2009 IEEE Workshop on Automatic Speech Recognition & Understanding, 432-437, 2009
252009
Learning feature mapping using deep neural network bottleneck features for distant large vocabulary speech recognition
I Himawan, P Motlicek, D Imseng, B Potard, N Kim, J Lee
2015 IEEE International Conference on Acoustics, Speech and Signal …, 2015
242015
MediaParl: Bilingual mixed language accented speech database
D Imseng, H Bourlard, H Caesar, PN Garner, G Lecorvé, A Nanchen
2012 IEEE Spoken Language Technology Workshop (SLT), 263-268, 2012
242012
Impact of deep MLP architecture on different acoustic modeling techniques for under-resourced speech recognition
D Imseng, P Motlicek, PN Garner, H Bourlard
2013 IEEE Workshop on Automatic Speech Recognition and Understanding, 332-337, 2013
232013
Language dependent universal phoneme posterior estimation for mixed language speech recognition
D Imseng, H Bourlard, MM Doss, J Dines
2011 IEEE International Conference on Acoustics, Speech and Signal …, 2011
232011
Preliminary work on speaker adaptation for DNN-based speech synthesis
B Potard, P Motlicek, D Imseng
Idiap, 2015
182015
Hierarchical multilayer perceptron based language identification
D Imseng, M Magimai Doss, H Bourlard
Proc. of Interspeech, 2722-2725, 2010
142010
Exploiting un-transcribed foreign data for speech recognition in well-resourced languages
D Imseng, B Potard, P Motlicek, A Nanchen, H Bourlard
2014 IEEE International Conference on Acoustics, Speech and Signal …, 2014
122014
Building context-dependent DNN acoustic models using Kullback-Leibler divergence-based state tying
G Gosztolya, T Grósz, L Tóth, D Imseng
2015 IEEE International Conference on Acoustics, Speech and Signal …, 2015
112015
Boosting Under-Resourced Speech Recognizers by Exploiting Out-Of-Language Data-Case Study on Afrikaans
D Imseng, H Bourlard, PN Garner
Spoken Language Technologies for Under-Resourced Languages, 2012
102012
Systemet kan inte utföra åtgärden just nu. Försök igen senare.
Artiklar 1–20