Contact Information

Brian Kingsbury
Research Staff Member, Advanced LVCSR Research
Thomas J. Watson Research Center, Yorktown Heights, NY USA
      +1dash914dash945dash2541


2013

Optimization Techniques to Improve Training Speed of Deep Belief Networks for Large Speech Tasks

Tara N Sainath, Brian Kingsbury, Hagen Soltau, Bhuvana Ramabhadran
IEEE, 2013

DEVELOPING KEYWORD SEARCH UNDER THE IARPA BABEL PROGRAM

Jonathan Mamou, Jia Cui, Xiaodong Cui, Mark JF Gales, Brian Kingsbury, Kate Knill, Lidia Mangu, David Nolden, Michael Picheny, Bhuvana Ramabhadran, others
Afeka Speech Processing Conference, 2013

Audio-visual deep learning for noise robust speech recognition

Jing Huang, Brian Kingsbury
Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference on, pp. 7596--7599

The IBM Speech Activity Detection System for the DARPA RATS Program

George Saon, Samuel Thomas, Hagen Soltau, Sriram Ganapathy, Brian Kingsbury
submitted to Interspeech, 2013

Accelerating Hessian-Free Optimization for Deep Neural Networks by Implicit Preconditioning and Sampling

Tara N Sainath, Lior Horesh, Brian Kingsbury, Aleksandr Y Aravkin, Bhuvana Ramabhadran
arXiv preprint arXiv:1309.1508, 2013

Improvements to deep convolutional neural networks for LVCSR

Tara N Sainath, Brian Kingsbury, Abdel-rahman Mohamed, George E Dahl, George Saon, Hagen Soltau, Tomas Beran, Aleksandr Y Aravkin, Bhuvana Ramabhadran
arXiv preprint arXiv:1309.1501, 2013

System combination and score normalization for spoken term detection

Jonathan Mamou, Jia Cui, Xiaodong Cui, Mark JF Gales, Brian Kingsbury, Kate Knill, Lidia Mangu, David Nolden, Michael Picheny, Bhuvana Ramabhadran, others
ICASSP, 2013

Low-rank matrix factorization for deep neural network training with high-dimensional output targets

Tara N Sainath, Brian Kingsbury, Vikas Sindhwani, Ebru Arisoy, Bhuvana Ramabhadran
Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference on, pp. 6655--6659

A HIGH-PERFORMANCE CANTONESE KEYWORD SEARCH SYSTEM

Brian Kingsbury, Jia Cui, Xiaodong Cui, Mark JF Gales, Kate Knill, Jonathan Mamou, Lidia Mangu, David Nolden, Michael Picheny, Bhuvana Ramabhadran, others
ICASSP, 2013

Developing speech recognition systems for corpus indexing under the IARPA Babel program

Jia Cui, Xiaodong Cui, J Mamou, B Kingsbury, B Ramabhadran, L Mangu, M Picheny, A Sethy, J Kim
ICASSP, 2013

Deep convolutional neural networks for LVCSR

Tara N Sainath, Abdel-rahman Mohamed, Brian Kingsbury, Bhuvana Ramabhadran
Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference on, pp. 8614--8618

New types of deep neural network learning for speech recognition and related applications: An overview

Li Deng, Geoffrey Hinton, Brian Kingsbury
Proc. ICASSP, 2013

Exploiting diversity for spoken term detection

Lidia Mangu, Hagen Soltau, Hong-Kwang Kuo, Brian Kingsbury, George Saon
Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference on, pp. 8282--8286

2012

Discriminative feature-space transforms using deep neural networks.

George Saon, Brian Kingsbury
INTERSPEECH, 2012

Domain adaptation in machine learning and speech processing

Fei Sha, Brian Kingsbury
Tutorial of Interspeech-2012, 1--214

Deep neural network language models

Ebru Arisoy, Tara N Sainath, Brian Kingsbury, Bhuvana Ramabhadran
Proceedings of the NAACL-HLT 2012 Workshop: Will We Ever Really Replace the N-gram Model? On the Future of Language Modeling for HLT, pp. 20--28

Auto-encoder bottleneck features using deep belief networks

Tara N Sainath, Brian Kingsbury, Bhuvana Ramabhadran
Acoustics, Speech and Signal Processing (ICASSP), 2012 IEEE International Conference on, pp. 4153--4156

Scalable Minimum Bayes Risk Training of Deep Neural Network Acoustic Models Using Distributed Hessian-free Optimization.

Brian Kingsbury, Tara N Sainath, Hagen Soltau
INTERSPEECH, 2012

Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups

Geoffrey Hinton, Li Deng, Dong Yu, George E Dahl, Abdel-rahman Mohamed, Navdeep Jaitly, Andrew Senior, Vincent Vanhoucke, Patrick Nguyen, Tara N Sainath, others
Signal Processing Magazine, IEEE 29(6), 82--97, IEEE, 2012

2011

The IBM 2011 GALE Arabic speech transcription system

Lidia Mangu, Hong-Kwang Kuo, Stephen Chu, Brian Kingsbury, George Saon, Hagen Soltau, Fadi Biadsy
Automatic Speech Recognition and Understanding (ASRU), 2011 IEEE Workshop on, pp. 272--277

Making deep belief networks effective for large vocabulary continuous speech recognition

Tara N Sainath, Brian Kingsbury, Bhuvana Ramabhadran, Petr Fousek, Petr Novak, A-r Mohamed
Automatic Speech Recognition and Understanding (ASRU), 2011 IEEE Workshop on, pp. 30--35

Trends and advances in speech recognition

Michael Picheny, David Nahamoo, Vaibhava Goel, Brian Kingsbury, Bhuvana Ramabhadran, Steven J Rennie, George Saon
IBM Journal of Research and Development 55(5), 2--1, IBM, 2011

Arccosine kernels: Acoustic modeling with infinite neural networks

Chih-Chieh Cheng, Brian Kingsbury
Acoustics, Speech and Signal Processing (ICASSP), 2011 IEEE International Conference on, pp. 5200--5203

The IBM 2009 GALE Arabic speech transcription system

Brian Kingsbury, Hagen Soltau, George Saon, Stephen Chu, Hong-Kwang Kuo, Lidia Mangu, Suman Ravuri, Nelson Morgan, Adam Janin
Acoustics, Speech and Signal Processing (ICASSP), 2011 IEEE International Conference on, pp. 4672--4675

Artificial intelligence research at IBM

James Fan, Michael Campbell, Brian Kingsbury
IBM Journal of Research and Development 55(5), 16--1, IBM, 2011

2010

Rapid and inexpensive development of speech action classifiers for natural language call routing systems

Ea-Ee Jan, Brian Kingsbury
Spoken Language Technology Workshop (SLT), 2010 IEEE, pp. 348--353

The IBM Attila speech recognition toolkit

Hagen Soltau, George Saon, Brian Kingsbury
Spoken Language Technology Workshop (SLT), 2010 IEEE, pp. 97--102

The IBM 2008 GALE Arabic speech transcription system

George Saon, Hagen Soltau, Upendra Chaudhari, Stephen Chu, Brian Kingsbury, Hong-Kwang Kuo, Lidia Mangu, Daniel Povey
Acoustics Speech and Signal Processing (ICASSP), 2010 IEEE International Conference on, pp. 4378--4381

2009

Fast decoding for open vocabulary spoken term detection

Bhuvana Ramabhadran, Abhinav Sethy, Jonathan Mamou, Brian Kingsbury, Upendra Chaudhari
Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Companion Volume: Short Papers, pp. 277--280, Association for Computational Linguistics

Tied-mixture language modeling in continuous space

Ruhi Sarikaya, Mohamed Afify, Brian Kingsbury
Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, pp. 459--467, Association for Computational Linguistics
Abstract

Lattice-based optimization of sequence classification criteria for neural-network acoustic modeling

Brian Kingsbury
Acoustics, Speech and Signal Processing, 2009. ICASSP 2009. IEEE International Conference on, pp. 3761--3764

Advances in Arabic speech transcription at IBM under the DARPA GALE program

Hagen Soltau, George Saon, Brian Kingsbury, H-KJ Kuo, Lidia Mangu, Daniel Povey, Ahmad Emami
Audio, Speech, and Language Processing, IEEE Transactions on 17(5), 884--894, IEEE, 2009

2008

Monte Carlo model-space noise adaptation for speech recognition.

Daniel Povey, Brian Kingsbury
INTERSPEECH, pp. 1281--1284, 2008

Machine translation in continuous space.

Ruhi Sarikaya, Yonggang Deng, Mohamed Afify, Brian Kingsbury, Yuqing Gao
INTERSPEECH, pp. 2350--2353, 2008

Discriminative graph training for ultra-fast low-footprint speech indexing.

Upendra V Chaudhari, Hong-Kwang Jeff Kuo, Brian Kingsbury
INTERSPEECH, pp. 2175--2178, 2008

Machine translation in continuous space

R Sarikaya, Y Deng, M Afify, B Kingsbury, Y Gao
Proc. Interspeech, 2008

Monte Carlo Model-Space Noise Adaptation for Speech Recognition

D Povey, B Kingsbury
Proc. Interspeech, pp. 1281-1284, 2008

Discriminative graph training for ultra-fast low-footprint speech indexing

U Chaudhari, H K J Kuo, B Kingsbury
Proc. Interspeech, pp. 2175--2178, 2008

Boosted MMI for model and feature-space discriminative training

Daniel Povey, Dimitri Kanevsky, Brian Kingsbury, Bhuvana Ramabhadran, George Saon, Karthik Visweswariah
Acoustics, Speech and Signal Processing, 2008. ICASSP 2008. IEEE International Conference on, pp. 4057--4060

2007

Discriminative training of decoding graphs for large vocabulary continuous speech recognition

H-KJ Kuo, Brian Kingsbury, Geoffrey Zweig
Acoustics, Speech and Signal Processing, 2007. ICASSP 2007. IEEE International Conference on, pp. IV--45

Evaluation of proposed modifications to MPE for large scale discriminative training

Daniel Povey, Brian Kingsbury
Acoustics, Speech and Signal Processing, 2007. ICASSP 2007. IEEE International Conference on, pp. IV--321

The IBM 2006 Gale Arabic ASR system

Hagen Soltau, George Saon, Brian Kingsbury, Jeff Kuo, Lidia Mangu, Daniel Povey, Geoffrey Zweig
Acoustics, Speech and Signal Processing, 2007. ICASSP 2007. IEEE International Conference on, pp. IV--349

2006

Pseudo pitch synchronous analysis of speech with applications to speaker recognition

Ran D Zilca, Brian Kingsbury, Jiri Navratil, Ganesh N Ramaswamy
Audio, Speech, and Language Processing, IEEE Transactions on 14(2), 467--478, IEEE, 2006

Automated quality monitoring for call centers using speech and NLP technologies

Geoffrey Zweig, Olivier Siohan, George Saon, Bhuvana Ramabhadran, Daniel Povey, Lidia Mangu, Brian Kingsbury
Proceedings of the 2006 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology: companion volume: demonstrations, pp. 292--295, Association for Computational Linguistics

Automated quality monitoring in the call center with asr and maximum entropy

Geoffrey Zweig, Olivier Siohan, George Saon, Bhuvana Ramabhadran, Daniel Povey, Lidia Mangu, Brian Kingsbury
Acoustics, Speech and Signal Processing, 2006. ICASSP 2006 Proceedings. 2006 IEEE International Conference on, pp. I--I

Advances in speech transcription at IBM under the DARPA EARS program

Stanley F Chen, Brian Kingsbury, Lidia Mangu, Daniel Povey, George Saon, Hagen Soltau, Geoffrey Zweig
Audio, Speech, and Language Processing, IEEE Transactions on 14(5), 1596--1608, IEEE, 2006

2005

Constructing ensembles of ASR systems using randomized decision trees

O Siohan, B Ramabhadran, B Kingsbury
ICASSP - IEEE International Conference on Acoustics, Speech, and Signal Processing, pp. 197--200, 2005

fMPE: Discriminatively trained features for speech recognition

Daniel Povey, Brian Kingsbury, Lidia Mangu, George Saon, Hagen Soltau, Geoffrey Zweig
ICASSP - IEEE International Conference on Acoustics, Speech, and Signal Processing, pp. 961--964, Philadelphia, 2005

The IBM 2004 conversational telephony system for rich transcription

Hagen Soltau, Brian Kingsbury, Lidia Mangu, Daniel Povey, George Saon, Geoffrey Zweig
ICASSP - IEEE International Conference on Acoustics, Speech, and Signal Processing, pp. 205--208, 2005

2004

Training a 2300-hour fisher system

Brian Kingsbury, Stan Chen, Lidia Mangu, Dan Povey, George Saon, Hagen Soltau, Geoffrey Zweig
EARS STT Workshop, 2004

An evaluation of a nonlinear feature transformation for conversational speech recognition

Mohamed Kamal Omar, Brian Kingsbury
Acoustics, Speech, and Signal Processing, 2004. Proceedings.(ICASSP'04). IEEE International Conference on, pp. I--785

2003

Large vocabulary conversational speech recognition with a subspace constraint on inverse covariance matrices.

Scott Axelrod, Vaibhava Goel, Brian Kingsbury, Karthik Visweswariah, Ramesh A Gopinath
INTERSPEECH, 2003

Toward domain-independent conversational speech recognition.

Brian Kingsbury, Lidia Mangu, George Saon, Geoffrey Zweig, Scott Axelrod, Vaibhava Goel, Karthik Visweswariah, Michael Picheny
INTERSPEECH, 2003

An architecture for rapid decoding of large vocabulary conversational speech.

George Saon, Geoffrey Zweig, Brian Kingsbury, Lidia Mangu, Upendra V Chaudhari
INTERSPEECH, 2003

Toward domain-independent conversational speech recognition

B. Kingsbury, L. Mangu, G. Saon, G. Zweig, S. Axelrod, V. Goel, K. Visweswariah, M. Picheny
Proc. Eurospeech, pp. 1881--1884, 2003

An architecture for rapid decoding of large vocabulary conversational speech

G Saon, G Zweig, B Kingsbury, L Mangu, U Chaudhari
Eighth European Conference on Speech Communication and Technology, 2003

Large vocabulary conversational speech recognition with a subspace constraint on inverse covariance matrices

S Axelrod, V Goel, B Kingsbury, K Visweswariah, R Gopinath
Eighth European Conference on Speech Communication and Technology, 2003

2002

Large vocabulary conversational speech recognition with the extended maximum likelihood linear transformation (EMLLT) model.

Jing Huang, Vaibhava Goel, Ramesh Gopinath, Brian Kingsbury, Peder A Olsen, Karthik Visweswariah
INTERSPEECH, 2002

Automatic speech recognition performance on a voicemail transcription task

Mukund Padmanabhan, George Saon, Jing Huang, Brian Kingsbury, Lidia Mangu
Speech and Audio Processing, IEEE Transactions on 10(7), 433--442, IEEE, 2002

A hybrid HMM/TRAPS model for robust voice activity detection

Brian Kingsbury, Pratibha Jain, Andre Adami
Seventh International Conference on Spoken Language Processing, 2002

Distributed speech recognition using noise-robust MFCC and TRAPS-estimated manner features

Pratibha Jain, Hynek Hermansky, Brian Kingsbury
Seventh International Conference on Spoken Language Processing, 2002

The SPRACHcore software package

D Ellis, JA Bilmes, E Fosler-Lussier, H Hermansky, D Johnson, B Kingsbury, N Morgan
Online, URL, 2002

Robust speech recognition in noisy environments: The 2001 IBM SPINE evaluation system

Brian Kingsbury, George Saon, Lidia Mangu, Mukund Padmanabhan, Ruhi Sarikaya
Acoustics, Speech, and Signal Processing (ICASSP), 2002 IEEE International Conference on, pp. I--53

Large vocabulary conversational speech recognition with the extended maximum likelihood linear transformation (EMLLT) model

J. Huang, V. Goel, R. Gopinath, B. Kingsbury, P. Olsen, K. Visweswariah
Seventh International Conference on Spoken Language Processing, pp. 2597--2600, 2002

2001

Evolution of the performance of automatic speech recognition algorithms in transcribing conversational telephone speech

M Padmanabhan, G Saon, G Zweig, J Huang, B Kingsbury, L Mangu
Instrumentation and Measurement Technology Conference, 2001. IMTC 2001. Proceedings of the 18th IEEE, pp. 1926--1931

2000

Recent improvements in speech recognition performance on large vocabulary conversational speech (voicemail and switchboard).

Jing Huang, Brian Kingsbury, Lidia Mangu, Mukund Padmanabhan, George Saon, Geoffrey Zweig
INTERSPEECH, pp. 338--341, 2000

Performance Improvements in Voicemail Transcription

J Huang, B Kingsbury, L Mangu, M Padmanabhan, G Saon, G Zweig
Proceedings of DARPA Speech Transcription Workshop, Citeseer, 2000

Recent improvements in speech recognition performance on large vocabulary conversational speech (voicemail and switchboard)

J Huang, B Kingsbury, L Mangu, M Padmanabhan, G Saon, G Zweig
Sixth International Conference on Spoken Language Processing, 2000

1999

The modulation-filtered spectrogram: a noise robust speech representation

B E D Kingsbury, N Morgan, S Greenberg
Workshop on Robust Methods for Speech Recognition in Adverse Conditions, pp. 95--98, 1999

An overview of the SPRACH system for the transcription of broadcast news

Gary Cook, James Christie, Dan Ellis, Eric Fosler-Lussier, Yoshihiko Gotoh, Brian Kingsbury, Nelson Morgan, Steve Renals, Tony Robinson, Gethin Williams
DARPA Broadcast News Workshop, 1999

Syllable-based speech recognition using auditorylike features

Steven Greenberg, Takayuki Arai, Brian Kingsbury, Nelson Morgan, Michael Shire, Rosaria Silipo, Su-Lin Wu
The Journal of the Acoustical Society of America105, 1157, 1999

Reducing errors by increasing the error rate: MLP Acoustic Modeling for Broadcast News Transcription

Nelson Morgan, Dan Ellis, Eric Fosler-Lussier, Adam Janin, Brian Kingsbury
Broadcast News Workshop'99 Proceedings, pp. 167, Morgan Kaufmann Pub, 1999

1998

Performance improvements through combining phone-and syllable-scale information in automatic speech recognition.

Su-Lin Wu, Brian Kingsbury, Nelson Morgan, Steven Greenberg
ICSLP, 1998

Incorporating information from syllable-length time scales into automatic speech recognition

S L Wu, ED Kingsbury, N Morgan, S Greenberg
ICASSP - IEEE International Conference on Acoustics, Speech, and Signal Processing, pp. 721--724, 1998

Robust speech recognition using the modulation spectrogram

Brian ED Kingsbury, Nelson Morgan, Steven Greenberg
Speech communication 25(1), 117--132, Elsevier, 1998

Performance improvements through combining phone-and syllable-scale information in automatic speech recognition

S L Wu, B E D Kingsbury, N Morgan, S Greenberg
Fifth International Conference on Spoken Language Processing, 1998

Parallel architectures for artificial neural networks: Paradigms and implementations

K Asanovic, J Beck, B Kingsbury, N Morgan, D Johnson, J Wawrzynek
chap. Training Neural Networks with SPERT-II). IEEE Computer Society Press and John Wiley \& Sons, 1998

1997

Recognizing reverberant speech with RASTA-PLP

Brian ED Kingsbury, Nelson Morgan
Acoustics, Speech, and Signal Processing, 1997. ICASSP-97., 1997 IEEE International Conference on, pp. 1259--1262

The modulation spectrogram: In pursuit of an invariant representation of speech

Steven Greenberg, Brian ED Kingsbury
Acoustics, Speech, and Signal Processing, 1997. ICASSP-97., 1997 IEEE International Conference on, pp. 1647--1650

Improving ASR performance for reverberant speech

Brian ED Kingsbury, Nelson Morgan, Steven Greenberg
in Proceedings of the ESCA Workshop on Robust Speech Recognition for Unknown Communication Channels, Pont-a-Mousson, pp. 87--90, Citeseer, 1997

1996

In search of an invariant representation for speech: The modulation spectrogram

Steven Greenberg, Brian E Kingsbury
The Journal of the Acoustical Society of America100, 2791, 1996

T0: A Single-Chip Vector Microprocessor with Reconfigurable Pipelines

Brian ED Kingsbury, John Wawrzynek
Solid-State Circuits Conference, 1996. ESSCIRC'96. Proceedings of the 22nd European, pp. 344--347

Spert-II: A vector microprocessor system

John Wawrzynek, Krste Asanovic, Brian Kingsbury, David Johnson, James Beck, Nelson Morgan
Computer 29(3), 79--86, IEEE, 1996

SPERT-II: A Vector Microprocessor System and its Application to Large Problems in Backpropagation Training

J Wawrzynek, K Asanovic, BED Kingsbury, J Beck, D Johnson, N Morgan
Advances in Neural Information Processing Systems 8, pp. 619-625, 1996

SPERT-II: A vector microprocessor system and its application to large problems in backpropagation training

John Wawrzynek, Krste Asanovic, Brian Kingsbury, James Beck, David Johnson, Nelson Morgan
Microelectronics for Neural Networks, 1996., Proceedings of Fifth International Conference on, pp. 227--231, Storming Media

1995

The T0 vector microprocessor

Krste Asanovic, James Beck, Bertrand Irissou, Brian Kingsbury, Nelson Morgan, John Wawrzynek
Proceedings of Hot Chips VII, pp. 187--196, 1995

SPERT: a neuro-microprocessor

Krste Asanovic, James Beck, Brian ED Kingsbury, Phil Kohn, Nelson Morgan, John Wawrzynek
Proceeding of an international workshop on VLSI for neural networks and artificial intelligence, pp. 103--107, Plenum Press, 1995

1993

CNS-1 Architecture Specification

Krste Asanovic, James Beck, Tim Callahan, Jerry Feldman, Bertrand Irissou, Brian Kingsbury, Phil Kohn, John Lazzaro, Nelson Morgan, David Stoutamire, others
EECS Department, UC Berkeley, 1993

CNS-1 architecture specification: A connectionist network supercomputer

K Asanovic, J Beck, T Callahan, J Feldman, B Irissou, B Kingsbury, P Kohn, J Lazzaro, N Morgan, D Stoutamire, others
Technical Report, 1993

1992

SPERT: A VLIW/SIM D

James Beck, Brian ED Kingsbury, Phil Kohn, Nelson Morgan, John Wawrzynek
1992

SPERT: A VLIW/SIMD Microprocessor for Artificial Neural Network Computations

James Beck, Brian ED Kingsbury, Phil Kohn, Nelson Morgan, John Wawrzynek
Application Specific Array Processors, 1992. Proceedings of the International Conference on, pp. 178--190, Citeseer

SPERT: a VLIW/SIMD neuro-microprocessor

K Asanovic, J Beck, BED Kingsbury, P Kohn, N Morgan, J Wawrzynek
Neural Networks, 1992. IJCNN., International Joint Conference on, pp. 577--582

1991

Recent work in VLSI elements for digital implementations of artificial neural networks

Brian ED Kingsbury, Bertrand Irissou, John Wawrzynek, Nelson Morgan
International Computer Science Institute, 1991

Using VOV, an automated design manager, in a VLSI design course

A Casotto, B Kingsbury, J Wawrzynek
Microelectronic System Education Conference and Exposition, 1991

1990

Developments in Digital VLSI Design for Artificial Neural Networks

Nelson Morgan1 Krste Asanovic, Brian Kingsbury, John Wawrzynek
1990