George Saon

5.0k citations

124 papers · 3.3k indexed · 2 hit papers · h-index 29

Impact in

Signal Processing top 0.2%
- Speech and Audio Processing
- Music and Audio Processing
Artificial Intelligence top 0.2%
- Speech Recognition and Synthesis
- Natural Language Processing Techniques
- Topic Modeling
- Speech and dialogue systems
- Neural Networks and Applications

Papers in

Signal Processing 73
- Speech and Audio Processing 61
- Music and Audio Processing 50
Artificial Intelligence 112
- Speech Recognition and Synthesis 102
- Natural Language Processing Techniques 37
- Speech and dialogue systems 14
- Topic Modeling 11
- Neural Networks and Applications 7

Co-authors: Hagen Soltau Brian Kingsbury Daniel Povey Michael Picheny Bhuvana Ramabhadran Geoffrey Zweig D. Nahamoo M. Padmanabhan
Journals: IBM Journal of Research and Development (3 papers)IEEE Transactions on Audio Speech and Language Processing (3 papers)IEEE Signal Processing Magazine (2 papers)IEEE Transactions on Speech and Audio Processing (2 papers)International Journal on Document Analysis and Recognition (IJDAR) (1 paper)
Partner nations: United States France Taiwan

In The Last Decade

George Saon

120 papers receiving 2.8k citations

Hit Papers

align trajectories log scale

Deep Convolutional Neural Networks for Large-scale Speech Tasks 2014 · 364 citations

What are hit papers?

Hit papers significantly outperform the citation benchmark for their cohort. A paper qualifies if any of the following hold:

it has ≥500 total citations;
it reaches ≥1.5× the top-1% citation threshold for papers in the same subfield and year (the threshold is the minimum needed to enter the top 1%, not the average within it);
it reaches the top citation threshold in at least one of its specific research topics.

2014 Neural Networks
2013 Speaker adaptation of neural network acoustic models using i-vectors

Peers

Countries citing papers authored by George Saon

Since Specialization

Citations

This map shows the geographic impact of George Saon's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by George Saon with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites George Saon more than expected).

Fields of papers citing papers by George Saon

Since Specialization

Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by George Saon. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by George Saon. The network helps show where George Saon may publish in the future.

Co-authorship network

The 25 scholars most cited alongside George Saon, linked wherever they have co-authored with each other. Click a name or a connecting line to browse the papers they share.

Border = papers with George Saon Line = papers co-authored together George Saon links everyone, so they are left out of the graph.

All Works

Sort: Min cites: Since: Top N: Style:

20 of 20 papers shown

#	Work
1	A Non-autoregressive Model for Joint STT and TTS Zhanar A. Zhagiparova, Brian Kingsbury, George Saon, Samuel Thomas, Slava Shechtman, Hagai Aronowitz, Eric Fosler‐Lussier, Luis Lastras	2025	1
2	LLM based Text Generation for Improved Low-resource Speech Recognition Models Tohru Nagano, Gakuto Kurata, Samuel Thomas, Hong-Kwang Jeff Kuo, Tammariello Rv, Hyun Chae Jung, George Saon	2025	1
3	Bilevel Joint Unsupervised and Supervised Training for Automatic Speech Recognition IEEE Transactions on Audio Speech and Language Processing ·Xiaodong Cui, A F M Saifuddin Saif, Songtao Lu, Lisha Chen, Tianyi Chen, Brian Kingsbury, George Saon	2024	0
4	Improving RNN Transducer Acoustic Models for English Conversational Speech Recognition Xiaodong Cui, George Saon, Brian Kingsbury	2023	1
5	Multi-Speaker Data Augmentation for Improved end-to-end Automatic Speech Recognition Samuel Thomas, Hong-Kwang Jeff Kuo, George Saon, Brian Kingsbury	2023	0
6	Speech-enriched Memory for Inference-time Adaptation of ASR Models to Word Dictionaries Zinnat Rahman, Sunita Sarawagi, Preethi Jyothi, George Saon, Gakuto Kurata	2023	1
7	Knowledge Distillation from Offline to Streaming RNN Transducer for End-to-End Speech Recognition Gakuto Kurata, George Saon	2020	28
8	Joint training of convolutional and non-convolutional neural networks Hagen Soltau, George Saon, Tara N. Sainath	2014	50
9	Analyzing convolutional neural networks for speech activity detection in mismatched acoustic conditions Samuel Thomas, Sriram Ganapathy, George Saon, Hagen Soltau	2014	70
10	Deep Convolutional Neural Networks for Large-scale Speech Tasks Neural Networks ·Tara N. Sainath, Brian Kingsbury, George Saon, Hagen Soltau, Abdelrahman Mohamed, George E. Dahl, Bhuvana Ramabhadran Hit paper breakdown →	2014	364
11	Bayesian sensing hidden Markov models for speech recognition George Saon, Jen‐Tzung Chien	2011	9
12	The IBM 2011 GALE Arabic speech transcription system Lidia Mangu, Hong-Kwang Jeff Kuo, Stephen M. Chu, Brian Kingsbury, George Saon, Hagen Soltau, Fadi Biadsy	2011	25
13	The IBM 2008 GALE Arabic speech transcription system George Saon, Hagen Soltau, Upendra V. Chaudhari, Stephen M. Chu, Brian Kingsbury, Hong-Kwang Jeff Kuo, Lidia Mangu, Daniel Povey	2010	22
14	Boosted MMI for model and feature-space discriminative training Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing ·Daniel Povey, Dimitri Kanevsky, Brian Kingsbury, Bhuvana Ramabhadran, George Saon, Karthik Visweswariah	2008	250
15	Robust speech recognition in Noisy Environments: The 2001 IBM spine evaluation system IEEE International Conference on Acoustics Speech and Signal Processing ·Brian Kingsbury, George Saon, Lidia Mangu, M. Padmanabhan, Ruhi Sarikaya	2002	37
16	Linear Feature Space Transformations for Speaker Adaptation International Conference on Acoustics, Speech, and Signal Processing ·George Saon, Geoffrey Zweig, M. Padmanabhan	2001	3
17	Minimum Bayes Error Feature Selection for Continuous Speech Recognition Neural Information Processing Systems ·George Saon, M. Padmanabhan	2000	38
18	Recent Improvements on a VoiceMail Transcription Task Conference of the International Speech Communication Association ·Mohamed Padmanabhan, George Saon, Sankar Basu, Jing Huang, Geoffrey Zweig	1999	2
19	Recognition of Unconstrained Handwritten Words using Markov Random Fields and HMMs HAL (Le Centre pour la Communication Scientifique Directe) ·George Saon, Abdel Belaı̈d	1995	2
20	Use of Stochastic Models in Text Recognition Abdel Belaı̈d, George Saon	1994	0

About George Saon

George Saon is a scholar working on Signal Processing, Artificial Intelligence, Computer Vision and Pattern Recognition, Media Technology and Ocean Engineering, having authored 124 papers that have together received 3.3k indexed citations. Recurring topics across this work include Speech Recognition and Synthesis (102 papers), Speech and Audio Processing (61 papers), Music and Audio Processing (50 papers), Natural Language Processing Techniques (37 papers), Speech and dialogue systems (14 papers), Topic Modeling (11 papers), Neural Networks and Applications (7 papers) and Handwritten Text Recognition Techniques (6 papers). The work is most often cited by research in Signal Processing (2.0k citations), Artificial Intelligence (2.8k citations), Computer Vision and Pattern Recognition (385 citations), Experimental and Cognitive Psychology (104 citations) and Computational Mathematics (4 citations). George Saon has collaborated with scholars based in United States, France and Taiwan. Frequent co-authors include Hagen Soltau, Brian Kingsbury, Daniel Povey, Michael Picheny, Bhuvana Ramabhadran, Geoffrey Zweig, D. Nahamoo, M. Padmanabhan, Lidia Mangu and Tara N. Sainath. Their work appears in journals such as IBM Journal of Research and Development, IEEE Transactions on Audio Speech and Language Processing, IEEE Signal Processing Magazine, IEEE Transactions on Speech and Audio Processing and International Journal on Document Analysis and Recognition (IJDAR).

Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.

Explore authors with similar magnitude of impact

Breakdown of academic impact, for papers by Dong YuBreakdown of academic impact, for papers by Yifan GongBreakdown of academic impact, for papers by Hagen SoltauBreakdown of academic impact, for papers by J.-L. GauvainBreakdown of academic impact, for papers by Zhizheng WuBreakdown of academic impact, for papers by Yanmin QianBreakdown of academic impact, for papers by Shigeru KatagiriBreakdown of academic impact, for papers by James Qin