Michael Levit

According to our database, Michael Levit authored at least 29 papers between 1999 and 2024.

Collaborative distances:

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

2024

Failing Forward: Improving Generative Error Correction for ASR with Synthetic Data and Retrieval Augmentation.

Sreyan Ghosh, Mohammad Sadegh Rasooli, Michael Levit, Peidong Wang, Jian Xue, Dinesh Manocha, Jinyu Li

CoRR, 2024

2023

External Language Model Integration for Factorized Neural Transducers.

Michael Levit, Sarangarajan Parthasarathy, Cem Aksoylar, Mohammad Sadegh Rasooli, Shuangyu Chang

CoRR, 2023

2018

What to Expect from Expected Kneser-Ney Smoothing.

Michael Levit, Sarangarajan Parthasarathy, Shuangyu Chang

Proceedings of the 19th Annual Conference of the International Speech Communication Association, 2018

2017

Don't Count on ASR to Transcribe for You: Breaking Bias with Two Crowds.

Michael Levit, Yan Huang, Shuangyu Chang, Yifan Gong

Proceedings of the 18th Annual Conference of the International Speech Communication Association, 2017

2016

Word-Phrase-Entity Recurrent Neural Networks for Language Modeling.

Michael Levit, Sarangarajan Parthasarathy, Shuangyu Chang

Proceedings of the 17th Annual Conference of the International Speech Communication Association, 2016

2015

Personalization of word-phrase-entity language models.

Michael Levit, Andreas Stolcke, R. Subba, Sarangarajan Parthasarathy, Shuangyu Chang, S. Xie, T. Anastasakos, Benoît Dumoulin

Proceedings of the 16th Annual Conference of the International Speech Communication Association, 2015

Token-level interpolation for class-based language models.

Michael Levit, Andreas Stolcke, Shuangyu Chang, Sarangarajan Parthasarathy

Proceedings of the 2015 IEEE International Conference on Acoustics, 2015

Discriminative training of context-dependent language model scaling factors and interpolation weights.

Shuangyu Chang, Abhik Lahiri, Issac Alphonso, Barlas Oguz, Michael Levit, Benoît Dumoulin

Proceedings of the 2015 IEEE Workshop on Automatic Speech Recognition and Understanding, 2015

2014

Word-phrase-entity language models: getting more mileage out of n-grams.

Michael Levit, Sarangarajan Parthasarathy, Shuangyu Chang, Andreas Stolcke, Benoît Dumoulin

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

2013

Improving unsupervised language model adaptation with discriminative data filtering.

Shuangyu Chang, Michael Levit, Partha Parthasarathy, Benoît Dumoulin

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

Accelerating recurrent neural network training via two stage classes and parallelization.

Zhiheng Huang, Geoffrey Zweig, Michael Levit, Benoît Dumoulin, Barlas Oguz, Shawn Chang

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

2012

End-to-end speech recognition accuracy metric for voice-search tasks.

Michael Levit, Shuangyu Chang, Bruce Buntschuh, Nick Kibre

Proceedings of the 2012 IEEE International Conference on Acoustics, 2012

2010

Leveraging call context information to improve confidence classification.

Michael Levit

Proceedings of the 2010 IEEE Spoken Language Technology Workshop, 2010

2009

IXIR: A statistical information distillation system.

Michael Levit, Dilek Hakkani-Tür, Gökhan Tür, Daniel Gillick

Comput. Speech Lang., 2009

Garbage modeling with decoys for a sequential recognition scenario.

Michael Levit, Shuangyu Chang, Bruce Buntschuh

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

2008

Unsupervised learning of edit parameters for matching name variants.

Daniel Gillick, Dilek Hakkani-Tür, Michael Levit

Proceedings of the 9th Annual Conference of the International Speech Communication Association, 2008

An iterative unsupervised learning method for information distillation.

Kamand Kamangar, Dilek Hakkani-Tür, Gökhan Tür, Michael Levit

Proceedings of the IEEE International Conference on Acoustics, 2008

2007

Interpretation of Spatial Language in a Map Navigation Task.

Michael Levit, Deb Roy

IEEE Trans. Syst. Man Cybern. Part B, 2007

Selecting on-topic sentences from natural language corpora.

Michael Levit, Elizabeth Boschee, Marjorie Freedman

Proceedings of the 8th Annual Conference of the International Speech Communication Association, 2007

Exploiting information extraction annotations for document retrieval in distillation tasks.

Dilek Hakkani-Tür, Gökhan Tür, Michael Levit

Proceedings of the 8th Annual Conference of the International Speech Communication Association, 2007

Integrating several annotation layers for statistical information distillation.

Michael Levit, Dilek Hakkani-Tür, Gökhan Tür, Daniel Gillick

Proceedings of the IEEE Workshop on Automatic Speech Recognition & Understanding, 2007

2006

The Human Speechome Project.

Deb Roy, Rupal Patel, Philip DeCamp, Rony Kubat, Michael Fleischman, Brandon Roy, Nikolaos Mavridis, Stefanie Tellex, Alexia Salata, Jethran Guinness, Michael Levit, Peter Gorniak

Proceedings of the Symbol Grounding and Beyond, 2006

2005

Spoken language understanding without transcriptions in a call center scenario.

Michael Levit

PhD thesis, 2005

"Of All Things the Measure Is Man" : Automatic Classification of Emotions and Inter-Labeler Consistency.

Stefan Steidl, Michael Levit, Anton Batliner, Elmar Nöth, Heinrich Niemann

Proceedings of the 2005 IEEE International Conference on Acoustics, 2005

2004

Aspects of named entity processing.

Michael Levit, Allen L. Gorin, Patrick Haffner, Hiyan Alshawi, Elmar Nöth

Proceedings of the 8th International Conference on Spoken Language Processing, 2004

2003

Context-sensitive evaluation and correction of phone recognition output.

Michael Levit, Hiyan Alshawi, Allen L. Gorin, Elmar Nöth

Proceedings of the 8th European Conference on Speech Communication and Technology, EUROSPEECH 2003, 2003

2002

Using EM-trained string-edit distances for approximate matching of acoustic morphemes.

Michael Levit, Elmar Nöth, Allen L. Gorin

Proceedings of the 7th International Conference on Spoken Language Processing, ICSLP2002, 2002

2001

Multipass algorithm for acquisition of salient acoustic morphemes.

Michael Levit, Allen L. Gorin, Jeremy H. Wright

Proceedings of the EUROSPEECH 2001 Scandinavia, 2001

1999

Discriminative estimation of interpolation parameters for language model classifiers.

Volker Warnke, Stefan Harbeck, Elmar Nöth, Heinrich Niemann, Michael Levit

Proceedings of the 1999 IEEE International Conference on Acoustics, 1999