logo Idiap Research Institute        
David Imseng
First name(s): David
Last name(s): Imseng

Publications of David Imseng
| 1 | 2 |

2017
2016
2015
Building context-dependent DNN acoustic models using Kullback-Leibler divergence-based state tying, Gábor Gosztolya, Tamás Grósz, László Tóth and David Imseng, in: Proceedings IEEE International Conference on Acoustics, Speech and Signal Processing, 2015
attachment
Exploiting foreign resources for DNN-based ASR, Petr Motlicek, David Imseng, Blaise Potard, Philip N. Garner and Ivan Himawan, in: EURASIP Journal on Audio, Speech, and Music Processing(2015:17), 2015
attachment
[DOI]
2014
Development of Bilingual ASR System for MediaParl Corpus, Petr Motlicek, David Imseng, Milos Cernak and Namhoon Kim, in: Proceedings of the 15th Annual Conference of the International Speech Communication Association (Interspeech 2014), Singapore, ISCA, 2014
attachment
Exploiting un-transcribed foreign data for speech recognition in well-resourced languages, David Imseng, Blaise Potard, Petr Motlicek, Alexandre Nanchen and Hervé Bourlard, in: Proceedings IEEE International Conference on Acoustics, Speech and Signal Processing, Florence, IT, pages 2322 - 2326, IEEE, 2014
attachment
[DOI]
Multilingual Deep Neural Network based Acoustic Modeling For Rapid Language Adaptation, Ngoc Thang Vu, David Imseng, Daniel Povey, Petr Motlicek, Tanja Schultz and Hervé Bourlard, in: Proceedings IEEE International Conference on Acoustics, Speech and Signal Processing, Florence, pages 7639-7643, IEEE, 2014
attachment
[DOI]
2013
Crosslingual Tandem-SGMM: Exploiting Out-Of-Language Data for Acoustic Model and Feature Level Adaptation, Petr Motlicek, David Imseng and Philip N. Garner, in: Proceedings of the 14th Annual Conference of the International Speech Communication Association (Interspeech 2013), ISCA - International Speech Communication Association, Lyon, France, pages 510-514, ISCA, 2013
attachment
Multilingual speech recognition A posterior based approach, David Imseng, École Polytechnique Fédérale de Lausanne (EPFL), 2013
attachment
Speaker adaptive Kullback-Leibler divergence based hidden Markov models, David Imseng and Hervé Bourlard, in: Proceedings IEEE International Conference on Acoustics, Speech and Signal Processing, 2013
attachment
2012
Boosting under-resourced speech recognizers by exploiting out of language data - Case study on Afrikaans, David Imseng, Hervé Bourlard and Philip N. Garner, in: Proceedings of the 3rd International Workshop on Spoken Languages Technologies for Under-resourced Languages, Cape Town, pages 60--67, 2012
attachment
MediaParl: Bilingual mixed language accented speech database, David Imseng, Hervé Bourlard, Holger Caesar, Philip N. Garner, Gwénolé Lecorvé and Alexandre Nanchen, in: Proceedings of the 2012 IEEE Workshop on Spoken Language Technology, pages 263--268, 2012
attachment
Robust triphone mapping for acoustic modeling, Milos Cernak, David Imseng and Hervé Bourlard, in: Proceedings of Interspeech, Portland, Oregon, 2012
attachment
The ICSI RT-09 Speaker Diarization System, Gerald Friedland, Adam Janin, David Imseng, Xavier Anguera, Luke Gottlieb, Marijn Huijbregts, Mary Tai Knox and Oriol Vinyals, in: IEEE Transactions on Audio, Speech, and Language Processing, 20(2):371--381, 2012
[DOI]
Using KL-divergence and multilingual information to improve ASR for under-resourced languages, David Imseng, Hervé Bourlard and Philip N. Garner, in: Proceedings IEEE International Conference on Acoustics, Speech and Signal Processing, Kyoto, pages 4869--4872, 2012
attachment
2011
| 1 | 2 |