Brian Kingsbury

发表

Deep Neural Networks for Acoustic Modeling in Speech Recognition

Tara N. Sainath, Brian Kingsbury, Geoffrey E. Hinton, 2012 .

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

Brian Kingsbury, Geoffrey E. Hinton, Li Deng, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

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

Brian Kingsbury, Brian Kingsbury, 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.

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

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

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

Tara N. Sainath, Brian Kingsbury, Bhuvana Ramabhadran, 2013, IEEE Transactions on Audio, Speech, and Language Processing.

Making Deep Belief Networks effective for large vocabulary continuous speech recognition

Tara N. Sainath, Brian Kingsbury, Bhuvana Ramabhadran, 2011, 2011 IEEE Workshop on Automatic Speech Recognition & Understanding.

Improvements to Deep Convolutional Neural Networks for LVCSR

Tara N. Sainath, Brian Kingsbury, Bhuvana Ramabhadran, 2013, 2013 IEEE Workshop on Automatic Speech Recognition and Understanding.

FUNDAMENTAL TECHNOLOGIES IN MODERN SPEECH RECOGNITION Digital Object Identifier 10.1109/MSP.2012.2205597

Tara N. Sainath, Brian Kingsbury, Geoffrey E. Hinton, 2012 .

Low-rank matrix factorization for Deep Neural Network training with high-dimensional output targets

Ebru Arisoy, Tara N. Sainath, Brian Kingsbury, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

Spert-II: A Vector Microprocessor System

Brian Kingsbury, John Wawrzynek, Krste Asanovic, 1996, Computer.

Deep Neural Network Language Models

Tara N. Sainath, T. Sainath, Brian Kingsbury, 2012, WLM@NAACL-HLT.

Boosted MMI for model and feature-space discriminative training

Brian Kingsbury, Bhuvana Ramabhadran, George Saon, 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

Auto-encoder bottleneck features using deep belief networks

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

Accelerating Hessian-free optimization for Deep Neural Networks by implicit preconditioning and sampling

Tara N. Sainath, Brian Kingsbury, Bhuvana Ramabhadran, 2013, 2013 IEEE Workshop on Automatic Speech Recognition and Understanding.

The shared views of four research groups )

Tara N. Sainath, Brian Kingsbury, Geoffrey E. Hinton, 2012 .

Evaluation of Proposed Modifications to MPE for Large Scale Discriminative Training

Brian Kingsbury, Daniel Povey, Brian Kingsbury, 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

The IBM Attila speech recognition toolkit

Brian Kingsbury, George Saon, Hagen Soltau, 2010, 2010 IEEE Spoken Language Technology Workshop.

Advances in speech transcription at IBM under the DARPA EARS program

Geoffrey Zweig, Brian Kingsbury, George Saon, 2006, IEEE Transactions on Audio, Speech, and Language Processing.

fMPE: discriminatively trained features for speech recognition

Geoffrey Zweig, Brian Kingsbury, George Saon, 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

4-bit Quantization of LSTM-based Speech Recognition Models pdf

Brian Kingsbury, George Saon, Swagath Venkataramani, 2021, Interspeech.

Single headed attention based sequence-to-sequence model for state-of-the-art results on Switchboard-300

Brian Kingsbury, G. Saon, Zoltán Tüske, 2020, INTERSPEECH.

Parallel Deep Neural Network Training for Big Data on Blue Gene/Q

Tara N. Sainath, Brian Kingsbury, Bhuvana Ramabhadran, 2017, IEEE Trans. Parallel Distributed Syst..

An architecture for rapid decoding of large vocabulary conversational speech

Geoffrey Zweig, Brian Kingsbury, George Saon, 2003, INTERSPEECH.

Deep Convolutional Neural Networks for Large-scale Speech Tasks

Tara N. Sainath, Brian Kingsbury, Bhuvana Ramabhadran, 2015, Neural Networks.

Tied-Mixture Language Modeling in Continuous Space

Brian Kingsbury, Ruhi Sarikaya, Mohamed Afify, 2009, NAACL.

Kernel Approximation Methods for Speech Recognition

Brian Kingsbury, Michael Picheny, Michael Collins, 2017, J. Mach. Learn. Res..

Recognizing reverberant speech with RASTA-PLP

Brian Kingsbury, Nelson Morgan, Brian Kingsbury, 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

An Overview of the SPRACH System for the Transcription of Broadcast News

Brian Kingsbury, Daniel P. W. Ellis, Steve Renals, 1999 .

Data Augmentation for deep neural network acoustic modeling

Xiaodong Cui, Brian Kingsbury, Vaibhava Goel, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Knowledge distillation across ensembles of multilingual models for low-resource languages

Brian Kingsbury, Bhuvana Ramabhadran, George Saon, 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Multimodal Clustering Networks for Self-supervised Learning from Unlabeled Videos pdf

James Glass, Brian Kingsbury, Michael Picheny, 2021, 2021 IEEE/CVF International Conference on Computer Vision (ICCV).

Tokenwise Contrastive Pretraining for Finer Speech-to-BERT Alignment in End-to-End Speech-to-Intent Systems

Brian Kingsbury, E. Fosler-Lussier, Samuel Thomas, 2022, INTERSPEECH.

Accelerating Inference and Language Model Fusion of Recurrent Neural Network Transducers via End-to-End 4-bit Quantization

Brian Kingsbury, K. Gopalakrishnan, G. Saon, 2022, ArXiv.

Improving training time of Hessian-free optimization for deep neural networks using preconditioning and sampling pdf

Tara N. Sainath, Brian Kingsbury, Bhuvana Ramabhadran, 2013, ArXiv.

Proceedings of the 1999 DARPA Broadcast News Workshop

Brian Kingsbury, Daniel P. W. Ellis, Steve Renals, 1999 .

CNS-1 Architecture Specification

Brian Kingsbury, John Wawrzynek, John Lazzaro, 1993 .

Everything at Once – Multi-modal Fusion Transformer for Video Retrieval

James R. Glass, Brian Kingsbury, R. Feris, 2021, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

VQ-T: RNN Transducers using Vector-Quantized Prediction Network States

Brian Kingsbury, G. Saon, Shinji Watanabe, 2022, INTERSPEECH.

C2KD: Cross-Lingual Cross-Modal Knowledge Distillation for Multilingual Text-Video Retrieval

James R. Glass, Brian Kingsbury, R. Feris, 2022, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

AVLnet: Learning Audio-Visual Language Representations from Instructional Videos

James R. Glass, A. Torralba, M. Picheny, 2020, Interspeech.

Beyond Backprop: Online Alternating Minimization with Auxiliary Variables

Brian Kingsbury, Viatcheslav Gurev, Djallel Bouneffouf, 2018, ICML.

On the limit of English conversational speech recognition pdf

Brian Kingsbury, George Saon, Zolt'an Tuske, 2021, Interspeech.

Single headed attention based sequence-to-sequence model for state-of-the-art results on Switchboard-300

Brian Kingsbury, George Saon, Kartik Audhkhasi, 2020, INTERSPEECH.

Pseudo Pitch Synchronous Analysis of Speech With Applications to Speaker Recognition

Brian Kingsbury, Jirí Navrátil, Ganesh N. Ramaswamy, 2006, IEEE Transactions on Audio, Speech, and Language Processing.

Audio-visual deep learning for noise robust speech recognition

Jing Huang, Brian Kingsbury, Brian Kingsbury, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

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

Steven Greenberg, Brian Kingsbury, Nelson Morgan, 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

Deep convolutional neural networks for LVCSR

Tara N. Sainath, Brian Kingsbury, Bhuvana Ramabhadran, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

Data Augmentation for Deep Neural Network Acoustic Modeling

Xiaodong Cui, Brian Kingsbury, Vaibhava Goel, 2015, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

Robust speech recognition using the modulation spectrogram

Steven Greenberg, Brian Kingsbury, Nelson Morgan, 1998, Speech Commun..

End-to-End Spoken Language Understanding Using Transformer Networks and Self-Supervised Pre-Trained Features pdf

Brian Kingsbury, Samuel Thomas, Edmilson Morais, 2020, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Learning filter banks within a deep neural network framework

Tara N. Sainath, Brian Kingsbury, Bhuvana Ramabhadran, 2013, 2013 IEEE Workshop on Automatic Speech Recognition and Understanding.

Artificial intelligence research at IBM

Brian Kingsbury, James Fan, Michael Campbell, 2011, IBM J. Res. Dev..

Integrating Dialog History into End-to-End Spoken Language Understanding Systems pdf

Brian Kingsbury, George Saon, Jatin Ganhotra, 2021, Interspeech.

Towards End-to-End Integration of Dialog History for Improved Spoken Language Understanding

Brian Kingsbury, E. Fosler-Lussier, Samuel Thomas, 2022, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Toward domain-independent conversational speech recognition

Geoffrey Zweig, Brian Kingsbury, George Saon, 2003, INTERSPEECH.

Very deep multilingual convolutional neural networks for LVCSR

Brian Kingsbury, Yann LeCun, Tom Sercu, 2015, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

A Kolmogorov Complexity Approach to Generalization in Deep Learning

Brian Kingsbury, Kush R. Varshney, Hazar Yueksel, 2019 .

Decentralized Bilevel Optimization for Personalized Client Learning

Brian Kingsbury, L. Horesh, M. Squillante, 2022, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Federated Acoustic Modeling for Automatic Speech Recognition

Xiaodong Cui, Brian Kingsbury, Songtao Lu, 2021, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

The T0 Vector Microprocessor

Brian Kingsbury, John Wawrzynek, Krste Asanovic, 2011 .

End-to-end ASR-free keyword search from speech

Brian Kingsbury, Bhuvana Ramabhadran, Andrew Rosenberg, 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

A Highly Efficient Distributed Deep Learning System For Automatic Speech Recognition pdf

Brian Kingsbury, George Saon, Michael Picheny, 2019, INTERSPEECH.

Distributed Deep Learning Strategies for Automatic Speech Recognition

Xiaodong Cui, Brian Kingsbury, George Saon, 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Comparison of Multilingual Self-Supervised and Weakly-Supervised Speech Pre-Training for Adaptation to Unseen Languages

Leonid Karlinsky, Rogerio Feris, Brian Kingsbury, 2023, 2305.12606.

Leveraging Unpaired Text Data for Training End-To-End Speech-to-Intent Systems

Brian Kingsbury, Michael Picheny, Samuel Thomas, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

End-to-End Spoken Language Understanding Without Full Transcripts

Brian Kingsbury, Samuel Thomas, Zvi Kons, 2020, INTERSPEECH.

Transliteration Based Data Augmentation for Training Multilingual ASR Acoustic Models in Low Resource Settings

Brian Kingsbury, Samuel Thomas, Kartik Audhkhasi, 2020, INTERSPEECH.

Cascaded Multilingual Audio-Visual Learning from Videos pdf

James Glass, Brian Kingsbury, Michael Picheny, 2021, Interspeech.

Advancing RNN Transducer Technology for Speech Recognition

Brian Kingsbury, George Saon, Zoltan Tueske, 2021, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Integrating Text Inputs for Training and Adapting RNN Transducer ASR Models

Brian Kingsbury, G. Saon, Samuel Thomas, 2022, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Building Competitive Direct Acoustics-to-Word Models for English Conversational Speech Recognition

Brian Kingsbury, Bhuvana Ramabhadran, George Saon, 2017, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Network architectures for multilingual speech representation learning

Xiaodong Cui, Brian Kingsbury, Bhuvana Ramabhadran, 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Improvements to the IBM speech activity detection system for the DARPA RATS program

Brian Kingsbury, George Saon, Hagen Soltau, 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Representation Based Meta-Learning for Few-Shot Spoken Intent Recognition

Brian Kingsbury, Samarth Bharadwaj, Shreya Khare, 2020, INTERSPEECH.

Multilingual representations for low resource speech recognition and keyword search

Brian Kingsbury, Bhuvana Ramabhadran, Michael Picheny, 2015, 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU).

English Broadcast News Speech Recognition by Humans and Machines

Brian Kingsbury, George Saon, Michael Picheny, 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

How to Scale Up Kernel Methods to Be As Good As Deep Neural Nets pdf

Brian Kingsbury, Michael Picheny, Michael Collins, 2014, ArXiv.

Efficient one-vs-one kernel ridge regression for speech recognition

Brian Kingsbury, Jie Chen, Kartik Audhkhasi, 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Constructing ensembles of ASR systems using randomized decision trees

Brian Kingsbury, Bhuvana Ramabhadran, Olivier Siohan, 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

Data augmentation for deep convolutional neural network acoustic modeling

Xiaodong Cui, Brian Kingsbury, Vaibhava Goel, 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Arccosine kernels: Acoustic modeling with infinite neural networks

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

Forget a Bit to Learn Better: Soft Forgetting for CTC-Based Automatic Speech Recognition

Brian Kingsbury, George Saon, Michael Picheny, 2019, INTERSPEECH.

Sequence Noise Injected Training for End-to-end Speech Recognition

Brian Kingsbury, George Saon, Kartik Audhkhasi, 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Improving Customization of Neural Transducers by Mitigating Acoustic Mismatch of Synthesized Audio

Brian Kingsbury, George Saon, David Haws, 2021, Interspeech.

Beyond Backprop: Alternating Minimization with co-Activation Memory pdf

Brian Kingsbury, Djallel Bouneffouf, Ronny Luss, 2018, ArXiv.

Deep convolutional neural networks for LVCSR

Tara N. Sainath, Abdel-rahman Mohamed, Brian Kingsbury, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

Fast Training of Deep Neural Networks for Speech Recognition

Brian Kingsbury, Guojing Cong, Chih-Chieh Yang, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Automated Quality Monitoring in the Call Center with ASR and Maximum Entropy

Geoffrey Zweig, Brian Kingsbury, Bhuvana Ramabhadran, 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.

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

Brian Kingsbury, Ea-Ee Jan, Brian Kingsbury, 2010, 2010 IEEE Spoken Language Technology Workshop.

Estimating Information Flow in Deep Neural Networks

Brian Kingsbury, Kristjan H. Greenewald, Ziv Goldfeld, 2018, ICML.

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

Steven Greenberg, Brian Kingsbury, Brian Kingsbury, 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

Automated Quality Monitoring for Call Centers using Speech and NLP Technologies

Geoffrey Zweig, Brian Kingsbury, Bhuvana Ramabhadran, 2006, NAACL.

A Stochastic Linearized Augmented Lagrangian Method for Decentralized Bilevel Optimization

Brian Kingsbury, L. Horesh, Mingyi Hong, 2022, NeurIPS.

Loss Landscape Dependent Self-Adjusting Learning Rates in Decentralized Stochastic Gradient Descent pdf

Brian Kingsbury, Mingrui Liu, Wei Zhang, 2021, ArXiv.

Improving Efficiency in Large-Scale Decentralized Distributed Training

Brian Kingsbury, George Saon, Michael Picheny, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Multilingual Data Selection for Low Resource Speech Recognition

Brian Kingsbury, Bhuvana Ramabhadran, Jia Cui, 2016, INTERSPEECH.

Towards Reducing the Need for Speech Training Data to Build Spoken Language Understanding Systems

Brian Kingsbury, G. Saon, Samuel Thomas, 2022, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Multi-Speaker Data Augmentation for Improved end-to-end Automatic Speech Recognition

Brian Kingsbury, G. Saon, Samuel Thomas, 2023, IEEE International Conference on Acoustics, Speech, and Signal Processing.

Improving deep neural network acoustic modeling for audio corpus indexing under the IARPA babel program

Xiaodong Cui, Brian Kingsbury, Bhuvana Ramabhadran, 2014, INTERSPEECH.

The IBM 2006 Gale Arabic ASR System

Geoffrey Zweig, Brian Kingsbury, George Saon, 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

Semi-Autoregressive Streaming ASR With Label Context

Brian Kingsbury, G. Saon, Siddhant Arora, 2023, 2309.10926.

Top Downloads in IEEE Xplore [Reader's Choice]

Tara N. Sainath, Geoffrey E. Hinton, George E. Dahl, 2017, IEEE Signal Processing Magazine.

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

Steven Greenberg, Brian Kingsbury, Nelson Morgan, 1998, ICSLP.

System combination and score normalization for spoken term detection

Xiaodong Cui, Brian Kingsbury, Bhuvana Ramabhadran, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

Asynchronous Decentralized Distributed Training of Acoustic Models

Brian Kingsbury, George Saon, Mingrui Liu, 2021, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

A comparison between deep neural nets and kernel acoustic models for speech recognition

Brian Kingsbury, Michael Picheny, Michael Collins, 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Trends and advances in speech recognition

Brian Kingsbury, Bhuvana Ramabhadran, George Saon, 2011, IBM J. Res. Dev..