David Imseng - RankMe

29 papers A 9C 3Misc 9Journal 6Unranked 2

Year	Rank	Type	Title / Venue / Authors
2016	J	`jnl`	Feature mapping using far-field microphones for distant speech recognition. Speech Commun. Ivan Himawan, Petr Motlícek, David Imseng, Sridha Sridharan
2015	Misc	`conf`	Building context-dependent DNN acoustic models using Kullback-Leibler divergence-based state tying. ICASSP Gábor Gosztolya, Tamás Grósz, László Tóth, David Imseng
2015	J	`jnl`	Exploiting foreign resources for DNN-based ASR. EURASIP J. Audio Speech Music. Process. Petr Motlícek, David Imseng, Blaise Potard, Philip N. Garner, Ivan Himawan
2015	Misc	`conf`	Learning feature mapping using deep neural network bottleneck features for distant large vocabulary speech recognition. ICASSP Ivan Himawan, Petr Motlícek, David Imseng, Blaise Potard, Namhoon Kim, Jaewon Lee
2014	A	`conf`	Automatic speech recognition and translation of a Swiss German dialect: Walliserdeutsch. INTERSPEECH Philip N. Garner, David Imseng, Thomas Meyer
2014	A	`conf`	Development of bilingual ASR system for MediaParl corpus. INTERSPEECH Petr Motlícek, David Imseng, Milos Cernak, Namhoon Kim
2014	Misc	`conf`	Exploiting un-transcribed foreign data for speech recognition in well-resourced languages. ICASSP David Imseng, Blaise Potard, Petr Motlícek, Alexandre Nanchen, Hervé Bourlard
2014	Misc	`conf`	Multilingual deep neural network based acoustic modeling for rapid language adaptation. ICASSP Ngoc Thang Vu, David Imseng, Daniel Povey, Petr Motlícek, Tanja Schultz, Hervé Bourlard
2014	A	`conf`	Posterior-based sparse representation for automatic speech recognition. INTERSPEECH Sara Bahaadini, Afsaneh Asaei, David Imseng, Hervé Bourlard
2014	J	`jnl`	Using out-of-language data to improve an under-resourced speech recognizer. Speech Commun. David Imseng, Petr Motlícek, Hervé Bourlard, Philip N. Garner
2013	J	`jnl`	Applying Multi- and Cross-Lingual Stochastic Phone Space Transformations to Non-Native Speech Recognition. IEEE Trans. Speech Audio Process. David Imseng, Hervé Bourlard, John Dines, Philip N. Garner, Mathew Magimai-Doss
2013	A	`conf`	Crosslingual tandem-SGMM: exploiting out-of-language data for acoustic model and feature level adaptation. INTERSPEECH Petr Motlícek, David Imseng, Philip N. Garner
2013	C	`conf`	Impact of deep MLP architecture on different acoustic modeling techniques for under-resourced speech recognition. ASRU David Imseng, Petr Motlícek, Philip N. Garner, Hervé Bourlard
2013	Misc	`conf`	Speaker adaptive Kullback-Leibler divergence based hidden Markov models. ICASSP David Imseng, Hervé Bourlard
2012	—	`conf`	Boosting under-resourced speech recognizers by exploiting out-of-language data - case study on Afrikaans. SLTU David Imseng, Hervé Bourlard, Philip N. Garner
2012	A	`conf`	Comparing different acoustic modeling techniques for multilingual boosting. INTERSPEECH David Imseng, John Dines, Petr Motlícek, Philip N. Garner, Hervé Bourlard
2012	—	`conf`	MediaParl: Bilingual mixed language accented speech database. SLT David Imseng, Hervé Bourlard, Holger Caesar, Philip N. Garner, Gwénolé Lecorvé, Alexandre Nanchen
2012	A	`conf`	Robust triphone mapping for acoustic modeling. INTERSPEECH Milos Cernak, David Imseng, Hervé Bourlard
2012	J	`jnl`	The ICSI RT-09 Speaker Diarization System. IEEE Trans. Speech Audio Process. Gerald Friedland, Adam Janin, David Imseng, Xavier Anguera Miró, Luke R. Gottlieb, Marijn Huijbregts, Mary Tai Knox, Oriol Vinyals
2012	Misc	`conf`	Using KL-divergence and multilingual information to improve ASR for under-resourced languages. ICASSP David Imseng, Hervé Bourlard, Philip N. Garner
2011	C	`conf`	Fast and flexible Kullback-Leibler divergence based acoustic modeling for non-native speech recognition. ASRU David Imseng, Ramya Rasipuram, Mathew Magimai-Doss
2011	A	`conf`	Improving Non-Native ASR Through Stochastic Multilingual Phoneme Space Transformations. INTERSPEECH David Imseng, Hervé Bourlard, John Dines, Philip N. Garner, Mathew Magimai-Doss
2011	Misc	`conf`	Language dependent universal phoneme posterior estimation for mixed language speech recognition. ICASSP David Imseng, Hervé Bourlard, Mathew Magimai-Doss, John Dines
2010	Misc	`conf`	An adaptive initialization method for speaker Diarization based on prosodic features. ICASSP David Imseng, Gerald Friedland
2010	A	`conf`	Hierarchical multilayer perceptron based language identification. INTERSPEECH David Imseng, Mathew Magimai-Doss, Hervé Bourlard
2010	Misc	`conf`	Leveraging speaker diarization for meeting recognition from distant microphones. ICASSP Andreas Stolcke, Gerald Friedland, David Imseng
2010	A	`conf`	Towards mixed language speech recognition systems. INTERSPEECH David Imseng, Hervé Bourlard, Mathew Magimai-Doss
2010	J	`jnl`	Tuning-Robust Initialization Methods for Speaker Diarization. IEEE Trans. Speech Audio Process. David Imseng, Gerald Friedland
2009	C	`conf`	Robust Speaker Diarization for short speech recordings. ASRU David Imseng, Gerald Friedland