David Imseng

According to our database, David Imseng authored at least 29 papers between 2009 and 2016.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2016

Feature mapping using far-field microphones for distant speech recognition.

Ivan Himawan, Petr Motlícek, David Imseng, Sridha Sridharan

Speech Commun., 2016

2015

Exploiting foreign resources for DNN-based ASR.

Petr Motlícek, David Imseng, Blaise Potard, Philip N. Garner, Ivan Himawan

EURASIP J. Audio Speech Music. Process., 2015

Learning feature mapping using deep neural network bottleneck features for distant large vocabulary speech recognition.

Ivan Himawan, Petr Motlícek, David Imseng, Blaise Potard, Namhoon Kim, Jaewon Lee

Proceedings of the 2015 IEEE International Conference on Acoustics, 2015

Building context-dependent DNN acoustic models using Kullback-Leibler divergence-based state tying.

Gábor Gosztolya, Tamás Grósz, László Tóth, David Imseng

Proceedings of the 2015 IEEE International Conference on Acoustics, 2015

2014

Using out-of-language data to improve an under-resourced speech recognizer.

David Imseng, Petr Motlícek, Hervé Bourlard, Philip N. Garner

Speech Commun., 2014

Development of bilingual ASR system for MediaParl corpus.

Petr Motlícek, David Imseng, Milos Cernak, Namhoon Kim

Proceedings of the 15th Annual Conference of the International Speech Communication Association, 2014

Automatic speech recognition and translation of a Swiss German dialect: Walliserdeutsch.

Philip N. Garner, David Imseng, Thomas Meyer

Proceedings of the 15th Annual Conference of the International Speech Communication Association, 2014

Posterior-based sparse representation for automatic speech recognition.

Sara Bahaadini, Afsaneh Asaei, David Imseng, Hervé Bourlard

Proceedings of the 15th Annual Conference of the International Speech Communication Association, 2014

Multilingual deep neural network based acoustic modeling for rapid language adaptation.

Ngoc Thang Vu, David Imseng, Daniel Povey, Petr Motlícek, Tanja Schultz, Hervé Bourlard

Proceedings of the IEEE International Conference on Acoustics, 2014

Exploiting un-transcribed foreign data for speech recognition in well-resourced languages.

David Imseng, Blaise Potard, Petr Motlícek, Alexandre Nanchen, Hervé Bourlard

Proceedings of the IEEE International Conference on Acoustics, 2014

2013

Applying Multi- and Cross-Lingual Stochastic Phone Space Transformations to Non-Native Speech Recognition.

David Imseng, Hervé Bourlard, John Dines, Philip N. Garner, Mathew Magimai-Doss

IEEE Trans. Speech Audio Process., 2013

Crosslingual tandem-SGMM: exploiting out-of-language data for acoustic model and feature level adaptation.

Petr Motlícek, David Imseng, Philip N. Garner

Proceedings of the 14th Annual Conference of the International Speech Communication Association, 2013

Speaker adaptive Kullback-Leibler divergence based hidden Markov models.

David Imseng, Hervé Bourlard

Proceedings of the IEEE International Conference on Acoustics, 2013

Impact of deep MLP architecture on different acoustic modeling techniques for under-resourced speech recognition.

David Imseng, Petr Motlícek, Philip N. Garner, Hervé Bourlard

Proceedings of the 2013 IEEE Workshop on Automatic Speech Recognition and Understanding, 2013

2012

The ICSI RT-09 Speaker Diarization System.

Gerald Friedland, Adam Janin, David Imseng, Xavier Anguera Miró, Luke R. Gottlieb, Marijn Huijbregts, Mary Tai Knox, Oriol Vinyals

IEEE Trans. Speech Audio Process., 2012

Boosting under-resourced speech recognizers by exploiting out-of-language data - case study on Afrikaans.

David Imseng, Hervé Bourlard, Philip N. Garner

Proceedings of the Third Workshop on Spoken Language Technologies for Under-resourced Languages, 2012

MediaParl: Bilingual mixed language accented speech database.

David Imseng, Hervé Bourlard, Holger Caesar, Philip N. Garner, Gwénolé Lecorvé, Alexandre Nanchen

Proceedings of the 2012 IEEE Spoken Language Technology Workshop (SLT), 2012

Comparing different acoustic modeling techniques for multilingual boosting.

David Imseng, John Dines, Petr Motlícek, Philip N. Garner, Hervé Bourlard

Proceedings of the 13th Annual Conference of the International Speech Communication Association, 2012

Robust triphone mapping for acoustic modeling.

Milos Cernak, David Imseng, Hervé Bourlard

Proceedings of the 13th Annual Conference of the International Speech Communication Association, 2012

Using KL-divergence and multilingual information to improve ASR for under-resourced languages.

David Imseng, Hervé Bourlard, Philip N. Garner

Proceedings of the 2012 IEEE International Conference on Acoustics, 2012

2011

Improving Non-Native ASR Through Stochastic Multilingual Phoneme Space Transformations.

David Imseng, Hervé Bourlard, John Dines, Philip N. Garner, Mathew Magimai-Doss

Proceedings of the 12th Annual Conference of the International Speech Communication Association, 2011

Language dependent universal phoneme posterior estimation for mixed language speech recognition.

David Imseng, Hervé Bourlard, Mathew Magimai-Doss, John Dines

Proceedings of the IEEE International Conference on Acoustics, 2011

Fast and flexible Kullback-Leibler divergence based acoustic modeling for non-native speech recognition.

David Imseng, Ramya Rasipuram, Mathew Magimai-Doss

Proceedings of the 2011 IEEE Workshop on Automatic Speech Recognition & Understanding, 2011

2010

Tuning-Robust Initialization Methods for Speaker Diarization.

David Imseng, Gerald Friedland

IEEE Trans. Speech Audio Process., 2010

Hierarchical multilayer perceptron based language identification.

David Imseng, Mathew Magimai-Doss, Hervé Bourlard

Proceedings of the 11th Annual Conference of the International Speech Communication Association, 2010

Towards mixed language speech recognition systems.

David Imseng, Hervé Bourlard, Mathew Magimai-Doss

Proceedings of the 11th Annual Conference of the International Speech Communication Association, 2010

Leveraging speaker diarization for meeting recognition from distant microphones.

Andreas Stolcke, Gerald Friedland, David Imseng

Proceedings of the IEEE International Conference on Acoustics, 2010

An adaptive initialization method for speaker Diarization based on prosodic features.

David Imseng, Gerald Friedland

Proceedings of the IEEE International Conference on Acoustics, 2010

2009

Robust Speaker Diarization for short speech recordings.

David Imseng, Gerald Friedland

Proceedings of the 2009 IEEE Workshop on Automatic Speech Recognition & Understanding, 2009