George Saon

Publication Activity (10 Years)

Years Active: 1994-2024
Publications (10 Years): 85

Top Venues

CoRR

ICASSP

INTERSPEECH

Interspeech

Publications

Ankit Gupta, George Saon, Brian Kingsbury
Exploring the limits of decoder-only models trained on public speech recognition corpora. CoRR (2024)
Siddhant Arora, George Saon, Shinji Watanabe, Brian Kingsbury
Semi-Autoregressive Streaming ASR with Label Context. ICASSP (2024)
Takuma Udagawa, Masayuki Suzuki, Gakuto Kurata, Masayasu Muraoka, George Saon
Multiple Representation Transfer from Large Language Models to End-to-End ASR Systems. ICASSP (2024)
Xiaodong Cui, George Saon, Brian Kingsbury
Improving RNN Transducer Acoustic Models for English Conversational Speech Recognition. INTERSPEECH (2023)
George Saon, Ankit Gupta, Xiaodong Cui
Diagonal State Space Augmented Transformers for Speech Recognition. CoRR (2023)
Samuel Thomas, Hong-Kwang Jeff Kuo, George Saon, Brian Kingsbury
Multi-Speaker Data Augmentation for Improved end-to-end Automatic Speech Recognition. ICASSP (2023)
Ashish R. Mittal, Sunita Sarawagi, Preethi Jyothi, George Saon, Gakuto Kurata
Speech-enriched Memory for Inference-time Adaptation of ASR Models to Word Dictionaries. EMNLP (2023)
Siddhant Arora, George Saon, Shinji Watanabe, Brian Kingsbury
Semi-Autoregressive Streaming ASR With Label Context. CoRR (2023)
George Saon, Ankit Gupta, Xiaodong Cui
Diagonal State Space Augmented Transformers for Speech Recognition. ICASSP (2023)
Takuma Udagawa, Masayuki Suzuki, Gakuto Kurata, Masayasu Muraoka, George Saon
Multiple Representation Transfer from Large Language Models to End-to-End ASR Systems. CoRR (2023)
Xiaodong Cui, Ashish Mittal, Songtao Lu, Wei Zhang, George Saon, Brian Kingsbury
Soft Random Sampling: A Theoretical and Empirical Analysis. CoRR (2023)
Thomas Bohnstingl, Ayush Garg, Stanislaw Wozniak, George Saon, Evangelos Eleftheriou, Angeliki Pantazi
Speech Recognition Using Biologically-Inspired Neural Networks. ICASSP (2022)
Samuel Thomas, Hong-Kwang Jeff Kuo, Brian Kingsbury, George Saon
Towards Reducing the Need for Speech Training Data To Build Spoken Language Understanding Systems. CoRR (2022)
Xiaodong Cui, George Saon, Tohru Nagano, Masayuki Suzuki, Takashi Fukuda, Brian Kingsbury, Gakuto Kurata
Improving Generalization of Deep Neural Network Acoustic Models with Length Perturbation and N-best Based Label Smoothing. CoRR (2022)
Takuma Udagawa, Masayuki Suzuki, Gakuto Kurata, Nobuyasu Itoh, George Saon
Effect and Analysis of Large-scale Language Model Rescoring on Competitive ASR Systems. INTERSPEECH (2022)
Zvi Kons, Hagai Aronowitz, Edmilson da Silva Morais, Matheus Damasceno, Hong-Kwang Kuo, Samuel Thomas, George Saon
Extending RNN-T-based speech recognition systems with emotion and language classification. CoRR (2022)
Xiaodong Cui, George Saon, Tohru Nagano, Masayuki Suzuki, Takashi Fukuda, Brian Kingsbury, Gakuto Kurata
Improving Generalization of Deep Neural Network Acoustic Models with Length Perturbation and N-best Based Label Smoothing. INTERSPEECH (2022)
Samuel Thomas, Brian Kingsbury, George Saon, Hong-Kwang Jeff Kuo
Integrating Text Inputs for Training and Adapting RNN Transducer ASR Models. ICASSP (2022)
Jiatong Shi, George Saon, David Haws, Shinji Watanabe, Brian Kingsbury
VQ-T: RNN Transducers using Vector-Quantized Prediction Network States. INTERSPEECH (2022)
Andrea Fasoli, Chia-Yu Chen, Mauricio J. Serrano, Swagath Venkataramani, George Saon, Xiaodong Cui, Brian Kingsbury, Kailash Gopalakrishnan
Accelerating Inference and Language Model Fusion of Recurrent Neural Network Transducers via End-to-End 4-bit Quantization. INTERSPEECH (2022)
Hong-Kwang Jeff Kuo, Zoltán Tüske, Samuel Thomas, Brian Kingsbury, George Saon
Improving End-to-end Models for Set Prediction in Spoken Language Understanding. ICASSP (2022)
Zvi Kons, Hagai Aronowitz, Edmilson da Silva Morais, Matheus Damasceno, Hong-Kwang Kuo, Samuel Thomas, George Saon
Extending RNN-T-based speech recognition systems with emotion and language classification. INTERSPEECH (2022)
Takashi Fukuda, Samuel Thomas, Masayuki Suzuki, Gakuto Kurata, George Saon, Brian Kingsbury
Global RNN Transducer Models For Multi-dialect Speech Recognition. INTERSPEECH (2022)
Samuel Thomas, Brian Kingsbury, George Saon, Hong-Kwang Jeff Kuo
Integrating Text Inputs For Training and Adapting RNN Transducer ASR Models. CoRR (2022)
Andrea Fasoli, Chia-Yu Chen, Mauricio J. Serrano, Swagath Venkataramani, George Saon, Xiaodong Cui, Brian Kingsbury, Kailash Gopalakrishnan
Accelerating Inference and Language Model Fusion of Recurrent Neural Network Transducers via End-to-End 4-bit Quantization. CoRR (2022)
Jiatong Shi, George Saon, David Haws, Shinji Watanabe, Brian Kingsbury
VQ-T: RNN Transducers using Vector-Quantized Prediction Network States. CoRR (2022)
Samuel Thomas, Hong-Kwang Jeff Kuo, Brian Kingsbury, George Saon
Towards Reducing the Need for Speech Training Data to Build Spoken Language Understanding Systems. ICASSP (2022)
Takuma Udagawa, Masayuki Suzuki, Gakuto Kurata, Nobuyasu Itoh, George Saon
Effect and Analysis of Large-scale Language Model Rescoring on Competitive ASR Systems. CoRR (2022)
Hong-Kwang Jeff Kuo, Zoltán Tüske, Samuel Thomas, Brian Kingsbury, George Saon
Improving End-to-End Models for Set Prediction in Spoken Language Understanding. CoRR (2022)
Samuel Thomas, Hong-Kwang Jeff Kuo, George Saon, Zoltán Tüske, Brian Kingsbury, Gakuto Kurata, Zvi Kons, Ron Hoory
RNN Transducer Models for Spoken Language Understanding. ICASSP (2021)
Xiaodong Cui, Wei Zhang, Abdullah Kayi, Mingrui Liu, Ulrich Finkler, Brian Kingsbury, George Saon, David S. Kung
Asynchronous Decentralized Distributed Training of Acoustic Models. IEEE ACM Trans. Audio Speech Lang. Process. 29 (2021)
Xiaodong Cui, Wei Zhang, Abdullah Kayi, Mingrui Liu, Ulrich Finkler, Brian Kingsbury, George Saon, David S. Kung
Asynchronous Decentralized Distributed Training of Acoustic Models. CoRR (2021)
Samuel Thomas, Hong-Kwang Jeff Kuo, George Saon, Zoltán Tüske, Brian Kingsbury, Gakuto Kurata, Zvi Kons, Ron Hoory
RNN Transducer Models For Spoken Language Understanding. CoRR (2021)
Zoltán Tüske, George Saon, Brian Kingsbury
On the Limit of English Conversational Speech Recognition. Interspeech (2021)
Andrea Fasoli, Chia-Yu Chen, Mauricio J. Serrano, Xiao Sun, Naigang Wang, Swagath Venkataramani, George Saon, Xiaodong Cui, Brian Kingsbury, Wei Zhang, Zoltán Tüske, Kailash Gopalakrishnan
4-Bit Quantization of LSTM-Based Speech Recognition Models. Interspeech (2021)
George Saon, Zoltán Tüske, Daniel Bolaños, Brian Kingsbury
Advancing RNN Transducer Technology for Speech Recognition. ICASSP (2021)
Zoltán Tüske, George Saon, Brian Kingsbury
On the limit of English conversational speech recognition. CoRR (2021)
Andrea Fasoli, Chia-Yu Chen, Mauricio J. Serrano, Xiao Sun, Naigang Wang, Swagath Venkataramani, George Saon, Xiaodong Cui, Brian Kingsbury, Wei Zhang, Zoltán Tüske, Kailash Gopalakrishnan
4-bit Quantization of LSTM-based Speech Recognition Models. CoRR (2021)
Xiaodong Cui, Brian Kingsbury, George Saon, David Haws, Zoltán Tüske
Reducing Exposure Bias in Training Recurrent Neural Network Transducers. Interspeech (2021)
Thomas Bohnstingl, Ayush Garg, Stanislaw Wozniak, George Saon, Evangelos Eleftheriou, Angeliki Pantazi
Towards efficient end-to-end speech recognition with biologically-inspired neural networks. CoRR (2021)
Jatin Ganhotra, Samuel Thomas, Hong-Kwang Jeff Kuo, Sachindra Joshi, George Saon, Zoltán Tüske, Brian Kingsbury
Integrating Dialog History into End-to-End Spoken Language Understanding Systems. CoRR (2021)
Xiaodong Cui, Brian Kingsbury, George Saon, David Haws, Zoltán Tüske
Reducing Exposure Bias in Training Recurrent Neural Network Transducers. CoRR (2021)
Jatin Ganhotra, Samuel Thomas, Hong-Kwang Jeff Kuo, Sachindra Joshi, George Saon, Zoltán Tüske, Brian Kingsbury
Integrating Dialog History into End-to-End Spoken Language Understanding Systems. Interspeech (2021)
Gakuto Kurata, George Saon, Brian Kingsbury, David Haws, Zoltán Tüske
Improving Customization of Neural Transducers by Mitigating Acoustic Mismatch of Synthesized Audio. Interspeech (2021)
George Saon, Zoltán Tüske, Daniel Bolaños, Brian Kingsbury
Advancing RNN Transducer Technology for Speech Recognition. CoRR (2021)
Wei Zhang, Xiaodong Cui, Abdullah Kayi, Mingrui Liu, Ulrich Finkler, Brian Kingsbury, George Saon, Youssef Mroueh, Alper Buyuktosunoglu, Payel Das, David S. Kung, Michael Picheny
Improving Efficiency in Large-Scale Decentralized Distributed Training. ICASSP (2020)
Xiaodong Cui, Wei Zhang, Ulrich Finkler, George Saon, Michael Picheny, David S. Kung
Distributed Training of Deep Neural Network Acoustic Models for Automatic Speech Recognition. CoRR (2020)
Zoltán Tüske, George Saon, Kartik Audhkhasi, Brian Kingsbury
Single headed attention based sequence-to-sequence model for state-of-the-art results on Switchboard-300. CoRR (2020)
Gakuto Kurata, George Saon
Knowledge Distillation from Offline to Streaming RNN Transducer for End-to-End Speech Recognition. INTERSPEECH (2020)
George Saon, Zoltán Tüske, Kartik Audhkhasi
Alignment-Length Synchronous Decoding for RNN Transducer. ICASSP (2020)
Zoltán Tüske, George Saon, Kartik Audhkhasi, Brian Kingsbury
Single Headed Attention Based Sequence-to-Sequence Model for State-of-the-Art Results on Switchboard. INTERSPEECH (2020)
Xiaodong Cui, Wei Zhang, Ulrich Finkler, George Saon, Michael Picheny, David S. Kung
Distributed Training of Deep Neural Network Acoustic Models for Automatic Speech Recognition: A comparison of current training strategies. IEEE Signal Process. Mag. 37 (3) (2020)
Wei Zhang, Xiaodong Cui, Abdullah Kayi, Mingrui Liu, Ulrich Finkler, Brian Kingsbury, George Saon, Youssef Mroueh, Alper Buyuktosunoglu, Payel Das, David S. Kung, Michael Picheny
Improving Efficiency in Large-Scale Decentralized Distributed Training. CoRR (2020)
George Saon, Zoltán Tüske, Kartik Audhkhasi, Brian Kingsbury
Sequence Noise Injected Training for End-to-end Speech Recognition. ICASSP (2019)
Samuel Thomas, Masayuki Suzuki, Yinghui Huang, Gakuto Kurata, Zoltán Tüske, George Saon, Brian Kingsbury, Michael Picheny, Tom Dibert, Alice Kaiser-Schatzlein, Bern Samko
English Broadcast News Speech Recognition by Humans and Machines. ICASSP (2019)
Wei Zhang, Xiaodong Cui, Ulrich Finkler, George Saon, Abdullah Kayi, Alper Buyuktosunoglu, Brian Kingsbury, David S. Kung, Michael Picheny
A Highly Efficient Distributed Deep Learning System For Automatic Speech Recognition. CoRR (2019)
Samuel Thomas, Masayuki Suzuki, Yinghui Huang, Gakuto Kurata, Zoltán Tüske, George Saon, Brian Kingsbury, Michael Picheny, Tom Dibert, Alice Kaiser-Schatzlein, Bern Samko
English Broadcast News Speech Recognition by Humans and Machines. CoRR (2019)
Wei Zhang, Xiaodong Cui, Ulrich Finkler, George Saon, Abdullah Kayi, Alper Buyuktosunoglu, Brian Kingsbury, David S. Kung, Michael Picheny
A Highly Efficient Distributed Deep Learning System for Automatic Speech Recognition. INTERSPEECH (2019)
Kartik Audhkhasi, George Saon, Zoltán Tüske, Brian Kingsbury, Michael Picheny
Forget a Bit to Learn Better: Soft Forgetting for CTC-Based Automatic Speech Recognition. INTERSPEECH (2019)
Wei Zhang, Xiaodong Cui, Ulrich Finkler, Brian Kingsbury, George Saon, David S. Kung, Michael Picheny
Distributed Deep Learning Strategies for Automatic Speech Recognition. ICASSP (2019)
Wei Zhang, Xiaodong Cui, Ulrich Finkler, Brian Kingsbury, George Saon, David S. Kung, Michael Picheny
Distributed Deep Learning Strategies For Automatic Speech Recognition. CoRR (2019)
George Saon, Zoltán Tüske, Kartik Audhkhasi, Brian Kingsbury, Michael Picheny, Samuel Thomas
Simplified LSTMS for Speech Recognition. ASRU (2019)
Zoltán Tüske, Kartik Audhkhasi, George Saon
Advancing Sequence-to-Sequence Based Speech Recognition. INTERSPEECH (2019)
Michael Picheny, Zoltán Tüske, Brian Kingsbury, Kartik Audhkhasi, Xiaodong Cui, George Saon
Challenging the Boundaries of Speech Recognition: The MALACH Corpus. INTERSPEECH (2019)
Michael Picheny, Zoltán Tüske, Brian Kingsbury, Kartik Audhkhasi, Xiaodong Cui, George Saon
Challenging the Boundaries of Speech Recognition: The MALACH Corpus. CoRR (2019)
Kartik Audhkhasi, Brian Kingsbury, Bhuvana Ramabhadran, George Saon, Michael Picheny
Building Competitive Direct Acoustics-to-Word Models for English Conversational Speech Recognition. ICASSP (2018)
Tom Sercu, George Saon, Jia Cui, Xiaodong Cui, Bhuvana Ramabhadran, Brian Kingsbury, Abhinav Sethy
Network architectures for multilingual speech representation learning. ICASSP (2017)
Kartik Audhkhasi, Andrew Rosenberg, George Saon, Abhinav Sethy, Bhuvana Ramabhadran, Stanley F. Chen, Michael Picheny
Recent progress in deep end-to-end models for spoken language processing. IBM J. Res. Dev. 61 (4-5) (2017)
Kartik Audhkhasi, Bhuvana Ramabhadran, George Saon, Michael Picheny, David Nahamoo
Direct Acoustics-to-Word Models for English Conversational Speech Recognition. CoRR (2017)
George Saon, Gakuto Kurata, Tom Sercu, Kartik Audhkhasi, Samuel Thomas, Dimitrios Dimitriadis, Xiaodong Cui, Bhuvana Ramabhadran, Michael Picheny, Lynn-Li Lim, Bergul Roomi, Phil Hall
English Conversational Telephone Speech Recognition by Humans and Machines. INTERSPEECH (2017)
Gakuto Kurata, Abhinav Sethy, Bhuvana Ramabhadran, George Saon
Empirical Exploration of Novel Architectures and Objectives for Language Models. INTERSPEECH (2017)
Kartik Audhkhasi, Brian Kingsbury, Bhuvana Ramabhadran, George Saon, Michael Picheny
Building competitive direct acoustics-to-word models for English conversational speech recognition. CoRR (2017)
Xiaodong Cui, Vaibhava Goel, George Saon
Embedding-Based Speaker Adaptive Training of Deep Neural Networks. INTERSPEECH (2017)
Gakuto Kurata, Bhuvana Ramabhadran, George Saon, Abhinav Sethy
Language modeling with highway LSTM. ASRU (2017)
Xiaodong Cui, Vaibhava Goel, George Saon
Embedding-Based Speaker Adaptive Training of Deep Neural Networks. CoRR (2017)
Gakuto Kurata, Bhuvana Ramabhadran, George Saon, Abhinav Sethy
Language Modeling with Highway LSTM. CoRR (2017)
Guojing Cong, Brian Kingsbury, Soumyadip Gosh, George Saon, Fan Zhou
Accelerating deep neural network learning for speech recognition on a cluster of GPUs. MLHPC@SC (2017)
Kartik Audhkhasi, Bhuvana Ramabhadran, George Saon, Michael Picheny, David Nahamoo
Direct Acoustics-to-Word Models for English Conversational Speech Recognition. INTERSPEECH (2017)
George Saon, Michael Picheny
Recent advances in conversational speech recognition using convolutional and recurrent neural networks. IBM J. Res. Dev. 61 (4-5) (2017)
Jia Cui, Brian Kingsbury, Bhuvana Ramabhadran, George Saon, Tom Sercu, Kartik Audhkhasi, Abhinav Sethy, Markus Nußbaum-Thom, Andrew Rosenberg
Knowledge distillation across ensembles of multilingual models for low-resource languages. ICASSP (2017)
George Saon, Gakuto Kurata, Tom Sercu, Kartik Audhkhasi, Samuel Thomas, Dimitrios Dimitriadis, Xiaodong Cui, Bhuvana Ramabhadran, Michael Picheny, Lynn-Li Lim, Bergul Roomi, Phil Hall
English Conversational Telephone Speech Recognition by Humans and Machines. CoRR (2017)
David Haws, Dimitrios Dimitriadis, George Saon, Samuel Thomas, Michael Picheny
On the importance of event detection for ASR. ICASSP (2016)
Masayuki Suzuki, Ryuki Tachibana, Samuel Thomas, Bhuvana Ramabhadran, George Saon
Domain Adaptation of CNN Based Acoustic Models Under Limited Resource Settings. INTERSPEECH (2016)
George Saon, Tom Sercu, Steven J. Rennie, Hong-Kwang Jeff Kuo
The IBM 2016 English Conversational Telephone Speech Recognition System. INTERSPEECH (2016)
George Saon, Tom Sercu, Steven J. Rennie, Hong-Kwang Jeff Kuo
The IBM 2016 English Conversational Telephone Speech Recognition System. CoRR (2016)
Nitish Shirish Keskar, George Saon
A nonmonotone learning rate strategy for SGD training of deep neural networks. ICASSP (2015)
Lidia Mangu, George Saon, Michael Picheny, Brian Kingsbury
Order-free spoken term detection. ICASSP (2015)
Jia Cui, George Saon, Bhuvana Ramabhadran, Brian Kingsbury
A multi-region deep neural network model in speech recognition. INTERSPEECH (2015)
George Saon, Hong-Kwang Jeff Kuo, Steven J. Rennie, Michael Picheny
The IBM 2015 English Conversational Telephone Speech Recognition System. CoRR (2015)
George Saon, Hong-Kwang Jeff Kuo, Steven J. Rennie, Michael Picheny
The IBM 2015 English conversational telephone speech recognition system. INTERSPEECH (2015)
Samuel Thomas, George Saon, Maarten Van Segbroeck, Shrikanth S. Narayanan
Improvements to the IBM speech activity detection system for the DARPA RATS program. ICASSP (2015)
Samuel Thomas, George Saon, Hong-Kwang Jeff Kuo, Lidia Mangu
The IBM BOLT speech transcription system. INTERSPEECH (2015)
Tara N. Sainath, Brian Kingsbury, George Saon, Hagen Soltau, Abdel-rahman Mohamed, George E. Dahl, Bhuvana Ramabhadran
Deep Convolutional Neural Networks for Large-scale Speech Tasks. Neural Networks 64 (2015)
Samuel Thomas, Sriram Ganapathy, George Saon, Hagen Soltau
Analyzing convolutional neural networks for speech activity detection in mismatched acoustic conditions. ICASSP (2014)
Tara N. Sainath, Brian Kingsbury, Abdel-rahman Mohamed, George Saon, Bhuvana Ramabhadran
Improvements to filterbank and delta learning within a deep neural network framework. ICASSP (2014)
Tara N. Sainath, I-Hsin Chung, Bhuvana Ramabhadran, Michael Picheny, John A. Gunnels, Brian Kingsbury, George Saon, Vernon Austel, Upendra V. Chaudhari
Parallel deep neural network training for LVCSR tasks using blue gene/Q. INTERSPEECH (2014)
George Saon, Hagen Soltau, Ahmad Emami, Michael Picheny
Unfolded recurrent neural networks for speech recognition. INTERSPEECH (2014)
Hagen Soltau, George Saon, Tara N. Sainath
Joint training of convolutional and non-convolutional neural networks. ICASSP (2014)
George Saon, Hagen Soltau
A comparison of two optimization techniques for sequence discriminative training of deep neural networks. ICASSP (2014)
George Saon
A distributed architecture for fast SGD sequence discriminative training of DNN acoustic models. SLT (2014)

George Saon.css-eqlu8i{font-size:small;padding-left:4px;}

Publication Activity (10 Years)

Top Topics

Top Venues

George Saon