G. Saon

发表

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.

A nonmonotone learning rate strategy for SGD training of deep neural networks

George Saon, Nitish Shirish Keskar, N. Keskar, 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

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.

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.

Arc Minimization in Finite State Decoding Graphs with Cross-Word Decoding Context

G. Zweig, G. Saon, François Yvon, 2004 .

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..

Maximum likelihood discriminant feature spaces

George Saon, Ramesh A. Gopinath, Mukund Padmanabhan, 2000, 2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100).

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.

Lattice-based Viterbi decoding techniques for speech translation

George Saon, Michael Picheny, M. Picheny, 2007, 2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU).

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.

The IBM 2015 English conversational telephone speech recognition system pdf

George Saon, Michael Picheny, Hong-Kwang Jeff Kuo, 2015, INTERSPEECH.

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).

Recurrent Neural Networks for Speech Recognition

M. Picheny, H. Soltau, G. Saon, 2014 .

Lattice-based unsupervised maximum likelihood linear regression for speaker adaptation

M. Padmanabhan, G. Zweig, G. Saon, 2008 .

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.

Linear Feature Space Transformations for Speaker Adaptation

Geoffrey Zweig, George Saon, Mukund Padmanabhan, 2001 .

Recent Improvements on a VoiceMail Transcription Task

Geoffrey Zweig, George Saon, Jing Huang, 1999 .

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

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

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

M. Picheny, D. Nahamoo, B. Ramabhadran, 2017, Interspeech.

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.

Advancing Sequence-to-Sequence Based Speech Recognition

George Saon, Kartik Audhkhasi, Zoltán Tüske, 2019, INTERSPEECH.

Towards efficient end-to-end speech recognition with biologically-inspired neural networks pdf

George Saon, Evangelos Eleftheriou, Ayush Garg, 2021, ArXiv.

Minimum Bayes Error Feature Selection for Continuous Speech Recognition

George Saon, Mukund Padmanabhan, M. Padmanabhan, 2000, NIPS.

Improvements to the IBM Aurora 2 multi-condition system

George Saon, Juan M. Huerta, G. Saon, 2002, INTERSPEECH.

Recent advances in conversational speech recognition using convolutional and recurrent neural networks

George Saon, Michael Picheny, M. Picheny, 2017, IBM J. Res. Dev..

Recent progress in deep end-to-end models for spoken language processing

Bhuvana Ramabhadran, George Saon, Michael Picheny, 2017, IBM J. Res. Dev..

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

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

Toward domain-independent conversational speech recognition

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

Speaker adaptation of neural network acoustic models using i-vectors

George Saon, Hagen Soltau, Michael Picheny, 2013, 2013 IEEE Workshop on Automatic Speech Recognition and Understanding.

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).

Knowledge Distillation from Offline to Streaming RNN Transducer for End-to-End Speech Recognition

George Saon, Gakuto Kurata, G. Saon, 2020, INTERSPEECH.

Alignment-Length Synchronous Decoding for RNN Transducer

George Saon, Kartik Audhkhasi, Zoltán Tüske, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Large-Vocabulary Continuous Speech Recognition Systems: A Look at Some Recent Advances

Jen-Tzung Chien, George Saon, G. Saon, 2012, IEEE Signal Processing Magazine.

Diagonal State Space Augmented Transformers for Speech Recognition

G. Saon, Xiaodong Cui, Ankit Gupta, 2023, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

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).

Effect and Analysis of Large-scale Language Model Rescoring on Competitive ASR Systems

G. Saon, Takuma Udagawa, Gakuto Kurata, 2022, INTERSPEECH.

English Conversational Telephone Speech Recognition by Humans and Machines

Xiaodong Cui, Bhuvana Ramabhadran, George Saon, 2017, INTERSPEECH.

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).

Bayesian Sensing Hidden Markov Models

Jen-Tzung Chien, George Saon, G. Saon, 2012, IEEE Transactions on Audio, Speech, and Language Processing.

Fractional Fourier transform features for speech recognition

George Saon, Ruhi Sarikaya, Yuqing Gao, 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.

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.

Real-time multilingual HMM training robust to channel variations

George Saon, Ea-Ee Jan, Salim Roukos, 2000, INTERSPEECH.

Data-driven approach to designing compound words for continuous speech recognition

George Saon, Mukund Padmanabhan, M. Padmanabhan, 2001, IEEE Trans. Speech Audio Process..

Language modeling with highway LSTM

Bhuvana Ramabhadran, George Saon, Gakuto Kurata, 2017, 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).

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.

Joint training of convolutional and non-convolutional neural networks

Tara N. Sainath, George Saon, Hagen Soltau, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Automated Quality Monitoring for Call Centers using Speech and NLP Technologies

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

Analyzing convolutional neural networks for speech activity detection in mismatched acoustic conditions

George Saon, Hagen Soltau, Samuel Thomas, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

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).

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.

Multiple Representation Transfer from Large Language Models to End-to-End ASR Systems

G. Saon, Masayasu Muraoka, Takuma Udagawa, 2023, ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

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.

Domain Adaptation of CNN Based Acoustic Models Under Limited Resource Settings

Bhuvana Ramabhadran, George Saon, Ryuki Tachibana, 2016, INTERSPEECH.

Semi-Autoregressive Streaming ASR With Label Context

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

Soft Random Sampling: A Theoretical and Empirical Analysis

G. Saon, Xiaodong Cui, Brian Kingsbury, 2023, ArXiv.

LATTICE-BASED UNSUPERVISED MLLR FOR SPEAKER ADAPTATION

Geoffrey Zweig, George Saon, Mukund Padmanabhan, 2000 .

Exploring the limits of decoder-only models trained on public speech recognition corpora

G. Saon, Ankit Gupta, Brian Kingsbury, 2024, 2402.00235.