What to Expect from Expected Kneser-Ney Smoothing
Michael Levit, Sarangarajan Parthasarathy, Shawn Chang
Interspeech 2018 | September 2018
Michael Levit
Principal Applied Scientist
Publications
Publications by Year
-
N-gram Smoothing on Expected Fractional Counts
Michael Levit, Sarangarajan Parthasarathy, Shawn Chang
MSR-TR-2018-16 | June 2018
-
Don’t Count on ASR to Transcribe for You: Breaking Bias with Two Crowds
Michael Levit, Yan Huang, Shawn Chang, Yifan Gong
Interspeech | August 2017
-
Word-Phrase-Entity Recurrent Neural Networks for Language Modeling
Michael Levit, Sarangarajan Parthasarathy, Shawn Chang
Interspeech 2016 | August 2016
-
Discriminative Training of Context-Dependent Language Model Scaling Factors and Interpolation Weights
Issac Alphonso, Michael Levit, Shawn Chang
Proc. ASRU | December 2015
End-to-End Crowdsourcing Approach for Unbiased High-Quality Transcription of Speech
Michael Levit, Shawn Chang
HCOMP, Proc. HCOMP | November 2015
Personalization of Word-Phrase-Entity Language Models
Michael Levit, Andreas Stolcke, R. Subba, Sarangarajan Parthasarathy, Shawn Chang, S. Xie, T. Anastasakos, B. Dumoulin
Proc. Interspeech | September 2015
Token-level Interpolation for Class-Based Language Models
Michael Levit, Andreas Stolcke, Shawn Chang, Sarangarajan Parthasarathy
Proc. IEEE ICASSP | April 2015
Proc. IEEE ICASSP
-
Word-Phrase-Entity Language Models: Getting More Mileage out of N-Grams
Michael Levit, Sarangarajan Parthasarathy, Shuangyu Chang, Andreas Stolcke, Benoît Dumoulin
Proc. Interspeech | September 2014
-
Accelerating Recurrent Neural Network Training via Two Stage Classes and Parallelization
Geoffrey Zweig, Michael Levit, Shawn Chang
ASRU | December 2013
Improving unsupervised language model adaptation with discriminative data filtering
Shawn Chang, Michael Levit, Sarangarajan Parthasarathy, Benoit Dumoulin
INTERSPEECH | August 2013
-
END-TO-END SPEECH RECOGNITION ACCURACY METRIC FOR VOICE-SEARCH TASKS
Michael Levit, Nick Kibre, Shawn Chang
ICASSP | March 2012
-
-
Garbage Modeling with Decoys for a Sequential Recognition Scenario
Michael Levit, Shawn Chang, Bruce Buntschuh
ASRU | December 2009
IXIR: A Statistical Information Distillation System
Michael Levit, Dilek Hakkani-Tür, Gokhan Tur, Daniel Gillick
Computer Speech & Language | September 2009, Vol 23: pp. 527-542
-
Unsupervised Learning of Edit Parameters for Matching Name Variants
Dilek Hakkani-Tür, Michael Levit
Proc. of Interspeech | September 2008
An Iterative Unsupervised Learning Method for Information Distillation
Dilek Hakkani-Tür, Gokhan Tur, Michael Levit
ICASSP, Proc. of ICASSP | March 2008
-
Integrating Several Annotation Layers for Statistical Information Distillation
Michael Levit, Dilek Hakkani-Tür, Gokhan Tur, Daniel Gillick
Proc. of ASRU | December 2007
Exploiting Information Extraction Annotations for Document Retrieval in Distillation Tasks
Michael Levit, Dilek Hakkani-Tür, Gokhan Tur
Interspeech, Proc. of Interspeech | August 2007
Selecting On-Topic Sentences from Natural Language Corpora
Michael Levit, Elizabeth Boschee, Marjorie Freedman
Proceedings of Interspeech | August 2007
Interpretation of Spatial Language in a Map Navigation Task
Michael Levit, Deb Roy
Transactions on Systems, Man and Cybernetics, Transactions on Systems, Man and Cybernetics, Part B | June 2007
-
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
Cognitive Science | June 2006
-
Spoken Language Understanding without Transcriptions in a Call Canter Scenario
June 2005
PhD Thesis: Logos Verlag | June 2005
Of All Things the Measure is Man: Automatic Classification of Emotions and Inter-labeler Consistency
Stefan Steidl, Michael Levit, Anton Batliner, Elmar Noth, Heinrich Niemann
Proc. of ICASSP | March 2005
Proc. of ICASSP
Der Einsatz Unterschiedlicher Klassifikationssysteme zur Rutschungserkennungs (in German)
January 2005
-
Aspects of Named Entity Processing
Proc. of ICSLP | October 2004
-
Context-Sensitive Evaluation and Correction of Phone Recognition Output
Proc. of Eurospeech | September 2003
Proc. of Eurospeech
-
USING EM-TRAINED STRING-EDIT DISTANCES FOR APPROXIMATE MATCHING OF ACOUSTIC MORPHEMES
Proc. of ICSLP | September 2002
-
Multipass algorithm for acquisition of salient acoustic morphemes
Michael Levit, A. L. Gorin, J. H. Wright
Proc. of Eurospeech | September 2001
Proc. of Eurospeech
Use of prosodic speech characteristics for automated detection of alcohol intoxication
ISCA Workshop on Prosody in Speech Recognition and Understanding, Workshop on Prosody in Speech Recognition and Understanding | October 2001
Workshop on Prosody in Speech Recognition and Understanding
-
Discriminative Estimation of Interpolation Parameters for Language Model Classifiers
Proc. of ICASSP | March 1999
Publications by Research Area
-
What to Expect from Expected Kneser-Ney Smoothing
Michael Levit, Sarangarajan Parthasarathy, Shawn Chang
Interspeech 2018 | September 2018
N-gram Smoothing on Expected Fractional Counts
Michael Levit, Sarangarajan Parthasarathy, Shawn Chang
MSR-TR-2018-16 | June 2018
Don’t Count on ASR to Transcribe for You: Breaking Bias with Two Crowds
Michael Levit, Yan Huang, Shawn Chang, Yifan Gong
Interspeech | August 2017
Word-Phrase-Entity Recurrent Neural Networks for Language Modeling
Michael Levit, Sarangarajan Parthasarathy, Shawn Chang
Interspeech 2016 | August 2016
Personalization of Word-Phrase-Entity Language Models
Michael Levit, Andreas Stolcke, R. Subba, Sarangarajan Parthasarathy, Shawn Chang, S. Xie, T. Anastasakos, B. Dumoulin
Proc. Interspeech | September 2015
Token-level Interpolation for Class-Based Language Models
Michael Levit, Andreas Stolcke, Shawn Chang, Sarangarajan Parthasarathy
Proc. IEEE ICASSP | April 2015
Proc. IEEE ICASSP
Word-Phrase-Entity Language Models: Getting More Mileage out of N-Grams
Michael Levit, Sarangarajan Parthasarathy, Shuangyu Chang, Andreas Stolcke, Benoît Dumoulin
Proc. Interspeech | September 2014
Improving unsupervised language model adaptation with discriminative data filtering
Shawn Chang, Michael Levit, Sarangarajan Parthasarathy, Benoit Dumoulin
INTERSPEECH | August 2013
IXIR: A Statistical Information Distillation System
Michael Levit, Dilek Hakkani-Tür, Gokhan Tur, Daniel Gillick
Computer Speech & Language | September 2009, Vol 23: pp. 527-542
Unsupervised Learning of Edit Parameters for Matching Name Variants
Dilek Hakkani-Tür, Michael Levit
Proc. of Interspeech | September 2008
An Iterative Unsupervised Learning Method for Information Distillation
Dilek Hakkani-Tür, Gokhan Tur, Michael Levit
ICASSP, Proc. of ICASSP | March 2008
Integrating Several Annotation Layers for Statistical Information Distillation
Michael Levit, Dilek Hakkani-Tür, Gokhan Tur, Daniel Gillick
Proc. of ASRU | December 2007
Selecting On-Topic Sentences from Natural Language Corpora
Michael Levit, Elizabeth Boschee, Marjorie Freedman
Proceedings of Interspeech | August 2007
Exploiting Information Extraction Annotations for Document Retrieval in Distillation Tasks
Michael Levit, Dilek Hakkani-Tür, Gokhan Tur
Interspeech, Proc. of Interspeech | August 2007
Interpretation of Spatial Language in a Map Navigation Task
Michael Levit, Deb Roy
Transactions on Systems, Man and Cybernetics, Transactions on Systems, Man and Cybernetics, Part B | June 2007
Aspects of Named Entity Processing
Proc. of ICSLP | October 2004
-
Multipass algorithm for acquisition of salient acoustic morphemes
Michael Levit, A. L. Gorin, J. H. Wright
Proc. of Eurospeech | September 2001
Proc. of Eurospeech
Discriminative Training of Context-Dependent Language Model Scaling Factors and Interpolation Weights
Issac Alphonso, Michael Levit, Shawn Chang
Proc. ASRU | December 2015
End-to-End Crowdsourcing Approach for Unbiased High-Quality Transcription of Speech
Michael Levit, Shawn Chang
HCOMP, Proc. HCOMP | November 2015
END-TO-END SPEECH RECOGNITION ACCURACY METRIC FOR VOICE-SEARCH TASKS
Michael Levit, Nick Kibre, Shawn Chang
ICASSP | March 2012
Leveraging Call Context Information to Improve Confidence Classification
SLT | December 2010
Garbage Modeling with Decoys for a Sequential Recognition Scenario
Michael Levit, Shawn Chang, Bruce Buntschuh
ASRU | December 2009
IXIR: A Statistical Information Distillation System
Michael Levit, Dilek Hakkani-Tür, Gokhan Tur, Daniel Gillick
Computer Speech & Language | September 2009, Vol 23: pp. 527-542
Unsupervised Learning of Edit Parameters for Matching Name Variants
Dilek Hakkani-Tür, Michael Levit
Proc. of Interspeech | September 2008
An Iterative Unsupervised Learning Method for Information Distillation
Dilek Hakkani-Tür, Gokhan Tur, Michael Levit
ICASSP, Proc. of ICASSP | March 2008
Integrating Several Annotation Layers for Statistical Information Distillation
Michael Levit, Dilek Hakkani-Tür, Gokhan Tur, Daniel Gillick
Proc. of ASRU | December 2007
Selecting On-Topic Sentences from Natural Language Corpora
Michael Levit, Elizabeth Boschee, Marjorie Freedman
Proceedings of Interspeech | August 2007
Exploiting Information Extraction Annotations for Document Retrieval in Distillation Tasks
Michael Levit, Dilek Hakkani-Tür, Gokhan Tur
Interspeech, Proc. of Interspeech | August 2007
Interpretation of Spatial Language in a Map Navigation Task
Michael Levit, Deb Roy
Transactions on Systems, Man and Cybernetics, Transactions on Systems, Man and Cybernetics, Part B | June 2007
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
Cognitive Science | June 2006
Spoken Language Understanding without Transcriptions in a Call Canter Scenario
June 2005
PhD Thesis: Logos Verlag | June 2005
Of All Things the Measure is Man: Automatic Classification of Emotions and Inter-labeler Consistency
Stefan Steidl, Michael Levit, Anton Batliner, Elmar Noth, Heinrich Niemann
Proc. of ICASSP | March 2005
Proc. of ICASSP
Aspects of Named Entity Processing
Proc. of ICSLP | October 2004
Context-Sensitive Evaluation and Correction of Phone Recognition Output
Proc. of Eurospeech | September 2003
Proc. of Eurospeech
USING EM-TRAINED STRING-EDIT DISTANCES FOR APPROXIMATE MATCHING OF ACOUSTIC MORPHEMES
Proc. of ICSLP | September 2002
Use of prosodic speech characteristics for automated detection of alcohol intoxication
ISCA Workshop on Prosody in Speech Recognition and Understanding, Workshop on Prosody in Speech Recognition and Understanding | October 2001
Workshop on Prosody in Speech Recognition and Understanding
-
End-to-End Crowdsourcing Approach for Unbiased High-Quality Transcription of Speech
Michael Levit, Shawn Chang
HCOMP, Proc. HCOMP | November 2015
Interpretation of Spatial Language in a Map Navigation Task
Michael Levit, Deb Roy
Transactions on Systems, Man and Cybernetics, Transactions on Systems, Man and Cybernetics, Part B | June 2007
Der Einsatz Unterschiedlicher Klassifikationssysteme zur Rutschungserkennungs (in German)
January 2005
Use of prosodic speech characteristics for automated detection of alcohol intoxication
ISCA Workshop on Prosody in Speech Recognition and Understanding, Workshop on Prosody in Speech Recognition and Understanding | October 2001
Workshop on Prosody in Speech Recognition and Understanding
-
Discriminative Estimation of Interpolation Parameters for Language Model Classifiers
Proc. of ICASSP | March 1999
Accelerating Recurrent Neural Network Training via Two Stage Classes and Parallelization
Geoffrey Zweig, Michael Levit, Shawn Chang
ASRU | December 2013
-
Garbage Modeling with Decoys for a Sequential Recognition Scenario
Michael Levit, Shawn Chang, Bruce Buntschuh
ASRU | December 2009
-
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
Cognitive Science | June 2006
-
Of All Things the Measure is Man: Automatic Classification of Emotions and Inter-labeler Consistency
Stefan Steidl, Michael Levit, Anton Batliner, Elmar Noth, Heinrich Niemann
Proc. of ICASSP | March 2005
Proc. of ICASSP
Publications by Type
-
Multipass algorithm for acquisition of salient acoustic morphemes
Michael Levit, A. L. Gorin, J. H. Wright
Proc. of Eurospeech | September 2001
Proc. of Eurospeech
Discriminative Estimation of Interpolation Parameters for Language Model Classifiers
Proc. of ICASSP | March 1999
What to Expect from Expected Kneser-Ney Smoothing
Michael Levit, Sarangarajan Parthasarathy, Shawn Chang
Interspeech 2018 | September 2018
Word-Phrase-Entity Recurrent Neural Networks for Language Modeling
Michael Levit, Sarangarajan Parthasarathy, Shawn Chang
Interspeech 2016 | August 2016
Discriminative Training of Context-Dependent Language Model Scaling Factors and Interpolation Weights
Issac Alphonso, Michael Levit, Shawn Chang
Proc. ASRU | December 2015
End-to-End Crowdsourcing Approach for Unbiased High-Quality Transcription of Speech
Michael Levit, Shawn Chang
HCOMP, Proc. HCOMP | November 2015
Personalization of Word-Phrase-Entity Language Models
Michael Levit, Andreas Stolcke, R. Subba, Sarangarajan Parthasarathy, Shawn Chang, S. Xie, T. Anastasakos, B. Dumoulin
Proc. Interspeech | September 2015
Token-level Interpolation for Class-Based Language Models
Michael Levit, Andreas Stolcke, Shawn Chang, Sarangarajan Parthasarathy
Proc. IEEE ICASSP | April 2015
Proc. IEEE ICASSP
Word-Phrase-Entity Language Models: Getting More Mileage out of N-Grams
Michael Levit, Sarangarajan Parthasarathy, Shuangyu Chang, Andreas Stolcke, Benoît Dumoulin
Proc. Interspeech | September 2014
Improving unsupervised language model adaptation with discriminative data filtering
Shawn Chang, Michael Levit, Sarangarajan Parthasarathy, Benoit Dumoulin
INTERSPEECH | August 2013
END-TO-END SPEECH RECOGNITION ACCURACY METRIC FOR VOICE-SEARCH TASKS
Michael Levit, Nick Kibre, Shawn Chang
ICASSP | March 2012
Leveraging Call Context Information to Improve Confidence Classification
SLT | December 2010
Garbage Modeling with Decoys for a Sequential Recognition Scenario
Michael Levit, Shawn Chang, Bruce Buntschuh
ASRU | December 2009
Unsupervised Learning of Edit Parameters for Matching Name Variants
Dilek Hakkani-Tür, Michael Levit
Proc. of Interspeech | September 2008
An Iterative Unsupervised Learning Method for Information Distillation
Dilek Hakkani-Tür, Gokhan Tur, Michael Levit
ICASSP, Proc. of ICASSP | March 2008
Integrating Several Annotation Layers for Statistical Information Distillation
Michael Levit, Dilek Hakkani-Tür, Gokhan Tur, Daniel Gillick
Proc. of ASRU | December 2007
Selecting On-Topic Sentences from Natural Language Corpora
Michael Levit, Elizabeth Boschee, Marjorie Freedman
Proceedings of Interspeech | August 2007
Exploiting Information Extraction Annotations for Document Retrieval in Distillation Tasks
Michael Levit, Dilek Hakkani-Tür, Gokhan Tur
Interspeech, Proc. of Interspeech | August 2007
Interpretation of Spatial Language in a Map Navigation Task
Michael Levit, Deb Roy
Transactions on Systems, Man and Cybernetics, Transactions on Systems, Man and Cybernetics, Part B | June 2007
Of All Things the Measure is Man: Automatic Classification of Emotions and Inter-labeler Consistency
Stefan Steidl, Michael Levit, Anton Batliner, Elmar Noth, Heinrich Niemann
Proc. of ICASSP | March 2005
Proc. of ICASSP
Der Einsatz Unterschiedlicher Klassifikationssysteme zur Rutschungserkennungs (in German)
January 2005
Aspects of Named Entity Processing
Proc. of ICSLP | October 2004
Context-Sensitive Evaluation and Correction of Phone Recognition Output
Proc. of Eurospeech | September 2003
Proc. of Eurospeech
USING EM-TRAINED STRING-EDIT DISTANCES FOR APPROXIMATE MATCHING OF ACOUSTIC MORPHEMES
Proc. of ICSLP | September 2002
Use of prosodic speech characteristics for automated detection of alcohol intoxication
ISCA Workshop on Prosody in Speech Recognition and Understanding, Workshop on Prosody in Speech Recognition and Understanding | October 2001
Workshop on Prosody in Speech Recognition and Understanding
-
N-gram Smoothing on Expected Fractional Counts
Michael Levit, Sarangarajan Parthasarathy, Shawn Chang
MSR-TR-2018-16 | June 2018
-
Don’t Count on ASR to Transcribe for You: Breaking Bias with Two Crowds
Michael Levit, Yan Huang, Shawn Chang, Yifan Gong
Interspeech | August 2017
Accelerating Recurrent Neural Network Training via Two Stage Classes and Parallelization
Geoffrey Zweig, Michael Levit, Shawn Chang
ASRU | December 2013
IXIR: A Statistical Information Distillation System
Michael Levit, Dilek Hakkani-Tür, Gokhan Tur, Daniel Gillick
Computer Speech & Language | September 2009, Vol 23: pp. 527-542
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
Cognitive Science | June 2006
-
Spoken Language Understanding without Transcriptions in a Call Canter Scenario
June 2005
PhD Thesis: Logos Verlag | June 2005