Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Brian Kingsbury

4-bit Quantization of LSTM-based Speech Recognition Models


Aug 27, 2021
Andrea Fasoli, Chia-Yu Chen, Mauricio Serrano, Xiao Sun, Naigang Wang, Swagath Venkataramani, George Saon, Xiaodong Cui, Brian Kingsbury, Wei Zhang, Zoltán Tüske, Kailash Gopalakrishnan

* 5 pages, 3 figures, Andrea Fasoli and Chia-Yu Chen equally contributed to this work. Paper accepted to Interspeech 2021 

  Access Paper or Ask Questions

Reducing Exposure Bias in Training Recurrent Neural Network Transducers


Aug 24, 2021
Xiaodong Cui, Brian Kingsbury, George Saon, David Haws, Zoltan Tuske

* accepted to Interspeech 2021 

  Access Paper or Ask Questions

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


Aug 18, 2021
Jatin Ganhotra, Samuel Thomas, Hong-Kwang J. Kuo, Sachindra Joshi, George Saon, Zoltán Tüske, Brian Kingsbury

* Interspeech 2021 

  Access Paper or Ask Questions

Representation based meta-learning for few-shot spoken intent recognition


Jun 29, 2021
Ashish Mittal, Samarth Bharadwaj, Shreya Khare, Saneem Chemmengath, Karthik Sankaranarayanan, Brian Kingsbury

* Accepted paper at Interspeech 2020, 21st Annual Conference of the International Speech Communication Association, Virtual Event, Shanghai, China, 25-29 October, 2020 

  Access Paper or Ask Questions

Multimodal Clustering Networks for Self-supervised Learning from Unlabeled Videos


May 05, 2021
Brian Chen, Andrew Rouditchenko, Kevin Duarte, Hilde Kuehne, Samuel Thomas, Angie Boggust, Rameswar Panda, Brian Kingsbury, Rogerio Feris, David Harwath, James Glass, Michael Picheny, Shih-Fu Chang


  Access Paper or Ask Questions

On the limit of English conversational speech recognition


May 03, 2021
Zoltán Tüske, George Saon, Brian Kingsbury


  Access Paper or Ask Questions

RNN Transducer Models For Spoken Language Understanding


Apr 08, 2021
Samuel Thomas, Hong-Kwang J. Kuo, George Saon, Zoltán Tüske, Brian Kingsbury, Gakuto Kurata, Zvi Kons, Ron Hoory

* To appear in the proceedings of ICASSP 2021 

  Access Paper or Ask Questions

Advancing RNN Transducer Technology for Speech Recognition


Mar 17, 2021
George Saon, Zoltan Tueske, Daniel Bolanos, Brian Kingsbury

* Accepted at ICASSP 2021 

  Access Paper or Ask Questions

Federated Acoustic Modeling For Automatic Speech Recognition


Feb 08, 2021
Xiaodong Cui, Songtao Lu, Brian Kingsbury

* Accepted by ICASSP 2021 

  Access Paper or Ask Questions

End-to-end spoken language understanding using transformer networks and self-supervised pre-trained features


Nov 16, 2020
Edmilson Morais, Hong-Kwang J. Kuo, Samuel Thomas, Zoltan Tuske, Brian Kingsbury

* 5 pages, 3 tables and 1 figure 

  Access Paper or Ask Questions

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


Oct 08, 2020
Yinghui Huang, Hong-Kwang Kuo, Samuel Thomas, Zvi Kons, Kartik Audhkhasi, Brian Kingsbury, Ron Hoory, Michael Picheny

* 5 pages, published in ICASSP 2020 

  Access Paper or Ask Questions

End-to-End Spoken Language Understanding Without Full Transcripts


Sep 30, 2020
Hong-Kwang J. Kuo, Zoltán Tüske, Samuel Thomas, Yinghui Huang, Kartik Audhkhasi, Brian Kingsbury, Gakuto Kurata, Zvi Kons, Ron Hoory, Luis Lastras

* 5 pages, to be published in Interspeech 2020 

  Access Paper or Ask Questions

AVLnet: Learning Audio-Visual Language Representations from Instructional Videos


Jun 16, 2020
Andrew Rouditchenko, Angie Boggust, David Harwath, Dhiraj Joshi, Samuel Thomas, Kartik Audhkhasi, Rogerio Feris, Brian Kingsbury, Michael Picheny, Antonio Torralba, James Glass


  Access Paper or Ask Questions

Improving Efficiency in Large-Scale Decentralized Distributed Training


Feb 04, 2020
Wei Zhang, Xiaodong Cui, Abdullah Kayi, Mingrui Liu, Ulrich Finkler, Brian Kingsbury, George Saon, Youssef Mroueh, Alper Buyuktosunoglu, Payel Das, David Kung, Michael Picheny

* 45th International Conference on Acoustics, Speech, and Signal Processing (ICASSP'2020) Oral 

  Access Paper or Ask Questions

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


Jan 20, 2020
Zoltán Tüske, George Saon, Kartik Audhkhasi, Brian Kingsbury

* 5 pages, 2 figures 

  Access Paper or Ask Questions

Challenging the Boundaries of Speech Recognition: The MALACH Corpus


Aug 09, 2019
Michael Picheny, Zóltan Tüske, Brian Kingsbury, Kartik Audhkhasi, Xiaodong Cui, George Saon

* Accepted for publication at INTERSPEECH 2019 

  Access Paper or Ask Questions

A Highly Efficient Distributed Deep Learning System For Automatic Speech Recognition


Jul 10, 2019
Wei Zhang, Xiaodong Cui, Ulrich Finkler, George Saon, Abdullah Kayi, Alper Buyuktosunoglu, Brian Kingsbury, David Kung, Michael Picheny

* INTERSPEECH 2019 

  Access Paper or Ask Questions

English Broadcast News Speech Recognition by Humans and Machines


Apr 30, 2019
Samuel Thomas, Masayuki Suzuki, Yinghui Huang, Gakuto Kurata, Zoltan Tuske, George Saon, Brian Kingsbury, Michael Picheny, Tom Dibert, Alice Kaiser-Schatzlein, Bern Samko

* \copyright 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works 

  Access Paper or Ask Questions

Distributed Deep Learning Strategies For Automatic Speech Recognition


Apr 10, 2019
Wei Zhang, Xiaodong Cui, Ulrich Finkler, Brian Kingsbury, George Saon, David Kung, Michael Picheny

* Published in ICASSP'19 

  Access Paper or Ask Questions

Understanding Unequal Gender Classification Accuracy from Face Images


Nov 30, 2018
Vidya Muthukumar, Tejaswini Pedapati, Nalini Ratha, Prasanna Sattigeri, Chai-Wah Wu, Brian Kingsbury, Abhishek Kumar, Samuel Thomas, Aleksandra Mojsilovic, Kush R. Varshney


  Access Paper or Ask Questions

Beyond Backprop: Online Alternating Minimization with Auxiliary Variables


Oct 24, 2018
Anna Choromanska, Sadhana Kumaravel, Ronny Luss, Irina Rish, Brian Kingsbury, Mattia Rigotti, Paolo DiAchille, Viatcheslav Gurev, Ravi Tejwani, Djallel Bouneffouf

* First four authors contributed equally to this work: A.C. - theory, manuscript, S.K. - code, experiments, R.L. - algorithm, experiments, I.R. - algorithm, manuscript 

  Access Paper or Ask Questions

Estimating Information Flow in Neural Networks


Oct 16, 2018
Ziv Goldfeld, Ewout van den Berg, Kristjan Greenewald, Igor Melnyk, Nam Nguyen, Brian Kingsbury, Yury Polyanskiy


  Access Paper or Ask Questions

Building competitive direct acoustics-to-word models for English conversational speech recognition


Dec 08, 2017
Kartik Audhkhasi, Brian Kingsbury, Bhuvana Ramabhadran, George Saon, Michael Picheny

* Submitted to IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018 

  Access Paper or Ask Questions

End-to-End ASR-free Keyword Search from Speech


Jan 13, 2017
Kartik Audhkhasi, Andrew Rosenberg, Abhinav Sethy, Bhuvana Ramabhadran, Brian Kingsbury

* Published in the IEEE 2017 International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2017), scheduled for 5-9 March 2017 in New Orleans, Louisiana, USA 

  Access Paper or Ask Questions

Kernel Approximation Methods for Speech Recognition


Jan 13, 2017
Avner May, Alireza Bagheri Garakani, Zhiyun Lu, Dong Guo, Kuan Liu, Aurélien Bellet, Linxi Fan, Michael Collins, Daniel Hsu, Brian Kingsbury, Michael Picheny, Fei Sha


  Access Paper or Ask Questions

A Comparison between Deep Neural Nets and Kernel Acoustic Models for Speech Recognition


Mar 18, 2016
Zhiyun Lu, Dong Guo, Alireza Bagheri Garakani, Kuan Liu, Avner May, Aurelien Bellet, Linxi Fan, Michael Collins, Brian Kingsbury, Michael Picheny, Fei Sha

* arXiv admin note: text overlap with arXiv:1411.4000 

  Access Paper or Ask Questions

Very Deep Multilingual Convolutional Neural Networks for LVCSR


Jan 23, 2016
Tom Sercu, Christian Puhrsch, Brian Kingsbury, Yann LeCun

* Accepted for publication at ICASSP 2016 

  Access Paper or Ask Questions

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


Jun 17, 2015
Zhiyun Lu, Avner May, Kuan Liu, Alireza Bagheri Garakani, Dong Guo, Aurélien Bellet, Linxi Fan, Michael Collins, Brian Kingsbury, Michael Picheny, Fei Sha


  Access Paper or Ask Questions

Accelerating Hessian-free optimization for deep neural networks by implicit preconditioning and sampling


Dec 10, 2013
Tara N. Sainath, Lior Horesh, Brian Kingsbury, Aleksandr Y. Aravkin, Bhuvana Ramabhadran

* this paper is not supposed to be posted publically before the conference in December due to company policy. another co-author was not informed of this and posted without the permission of the first author. pls remove 

  Access Paper or Ask Questions