Samuel Thomas

3.9k citations

110 papers · 2.4k indexed · h-index 27

Impact in

Signal Processing top 0.5%
- Speech and Audio Processing
- Music and Audio Processing
Artificial Intelligence top 0.5%
- Speech Recognition and Synthesis
- Natural Language Processing Techniques
- Topic Modeling
- Speech and dialogue systems

Papers in ⓘ

Artificial Intelligence 83
- Speech Recognition and Synthesis 72
- Natural Language Processing Techniques 14
- Speech and dialogue systems 12
- Topic Modeling 6
Signal Processing 70
- Speech and Audio Processing 65
- Music and Audio Processing 53
- Blind Source Separation Techniques 5

Co-authors: Hynek Heřmanský (33 shared papers)Sriram Ganapathy (25 shared papers)George Saon (13 shared papers)Richard C. Rose (6 shared papers)Ondřej Glembek (6 shared papers)Pinar Akyazi (5 shared papers)Ariya Rastrow (5 shared papers)Nagendra Kumar Goel (5 shared papers)
Journals: The Journal of the Acoustical Society of America (3 papers)IEEE Signal Processing Letters (2 papers)Frontiers in Plant Science (2 papers)Potato Research (1 paper)ISPRS Journal of Photogrammetry and Remote Sensing (1 paper)
Partner nations: United States Germany India

In The Last Decade

Samuel Thomas

102 papers receiving 2.1k citations

Peers

Replace Kandarpa Kumar Sarma with:

Kandarpa Kumar Sarma India

Hélio Pedrini Brazil

Xi Yin United States

Aharon Bar-Hillel Israel

Aaron Bostrom United Kingdom

Hui Xue China

Joonwhoan Lee South Korea

Anand Singh Jalal India

Tsung‐Yu Lin United States

Berrin Yanıkoğlu Türkiye

Samuel Thomas relative to Kandarpa Kumar Sarma India Kandarpa Kumar Sarma's profile →

Citations per field

00.5×2×3×4×4.8×

Kandarpa Kumar Sarma · 1×

×4.8 1k/277

SP

×4.6 2k/365

AI

×2.2 205/94

EE

×1.0 255/255

CVPR

×3.1 253/82

ECOLO

Citations per year

2016

2017

2018

2019

2020

2021

2022

2023

2024

2025

2026

Countries citing papers authored by Samuel Thomas

Since Specialization

Citations

This map shows the geographic impact of Samuel Thomas'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 Samuel Thomas with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Samuel Thomas more than expected).

Fields of papers citing papers by Samuel Thomas

Since Specialization

Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Samuel Thomas. 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 Samuel Thomas. The network helps show where Samuel Thomas may publish in the future.

Co-authors

The 25 scholars most cited alongside Samuel Thomas, 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 Samuel Thomas Line = papers co-authored together Samuel Thomas links everyone, so they are left out of the graph.

All Works

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

20 of 20 papers shown

Showing the 20 most-cited of 110 papers — load more, or switch the sort, to bring in the rest.

#	Work
1	High-Throughput Phenotyping of Plant Height: Comparing Unmanned Aerial Vehicles and Ground LiDAR Estimates Frontiers in Plant Science ·Simon Madec, Frédéric Baret, Benoît de Solan, Samuel Thomas, Dan Dutartre, S. Jézéquel, Matthieu Hemmerlé, Gallian Colombeau, Alexis Comar	2017	254
2	The subspace Gaussian mixture model—A structured model for speech recognition Computer Speech & Language ·Daniel Povey, Lukáš Burget, Mohit Agarwal, Pinar Akyazi, Kai Feng, Arnab Ghoshal, Ondřej Glembek, Nagendra Kumar Goel, Martin Karafiát, Ariya Rastrow, Richard C. Rose, Petr Schwarz, Samuel Thomas	2010	210
3	Efficient Knowledge Distillation from an Ensemble of Teachers Takashi Fukuda, Masayuki Suzuki, Gakuto Kurata, Samuel Thomas, Jia Cui, Bhuvana Ramabhadran	2017	149
4	Subspace Gaussian Mixture Models for speech recognition Infoscience (Ecole Polytechnique Fédérale de Lausanne) ·Daniel Povey, Lukáš Burget, Mohit Agarwal, Pinar Akyazi, Kai Feng, Arnab Ghoshal, Ondřej Glembek, Nagendra Kumar Goel, Martin Karafiát, Ariya Rastrow, Richard C. Rose, Petr Schwarz, Samuel Thomas	2010	124
5	Multilingual acoustic modeling for speech recognition based on subspace Gaussian Mixture Models Infoscience (Ecole Polytechnique Fédérale de Lausanne) ·Lukáš Burget, Petr Schwarz, Mohit Agarwal, Pinar Akyazi, Kai Feng, Arnab Ghoshal, Ondřej Glembek, Nagendra Kumar Goel, Martin Karafiát, Daniel Povey, Ariya Rastrow, Richard C. Rose, Samuel Thomas	2010	123
6	Deep neural network features and semi-supervised training for low resource speech recognition Samuel Thomas, Michael L. Seltzer, Kenneth Church, Hynek Heřmanský	2013	81
7	Multilingual MLP features for low-resource LVCSR systems Samuel Thomas, Sriram Ganapathy, Hynek Heřmanský	2012	80
8	Analyzing convolutional neural networks for speech activity detection in mismatched acoustic conditions Samuel Thomas, Sriram Ganapathy, George Saon, Hagen Soltau	2014	70
9	Estimating wheat green area index from ground-based LiDAR measurement using a 3D canopy structure model Agricultural and Forest Meteorology ·Shouyang Liu, Frédéric Baret, Mariem Abichou, Frédéric Boudon, Samuel Thomas, Kaiguang Zhao, Christian Fournier, Bruno Andrieu, Kamran Irfan, Matthieu Hemmerlé, Benoît de Solan	2017	63
10	Recognition of Reverberant Speech Using Frequency Domain Linear Prediction IEEE Signal Processing Letters ·Samuel Thomas, Sriram Ganapathy, Hynek Heřmanský	2008	60
11	Cross-lingual and multi-stream posterior features for low resource LVCSR systems Samuel Thomas, Sriram Ganapathy, Hynek Heřmanský	2010	54
12	Rapid evaluation of speech representations for spoken term discovery Michael A. Carlin, Samuel Thomas, Aren Jansen, Hynek Heřmanský	2011	52
13	Multimodal Clustering Networks for Self-supervised Learning from Unlabeled Videos 2021 IEEE/CVF International Conference on Computer Vision (ICCV) ·Brian Chen, Andrew Rouditchenko, Kevin Duarte, Hilde Kuehne, Samuel Thomas, Angie Boggust, Rameswar Panda, Brian Kingsbury, Rogério Feris, David Harwath, James Glass, Michael Picheny, Shih-Fu Chang	2021	46
14	Emerging Global Trends in Advanced Manufacturing Philosophical transactions of the Royal Society of London. Series B, Biological sciences ·Stephanie Shipp, Nayanee Gupta, Bhavya Lal, J.A. Scott, Christopher L. Weber, Michael S. Finnin, Meredith Blake, Sherrica Newsome, Samuel Thomas	2012	44
15	The IBM speech activity detection system for the DARPA RATS program George Saon, Samuel Thomas, Hagen Soltau, Sriram Ganapathy, Brian Kingsbury	2013	38
16	Annealed dropout training of deep networks Steven J. Rennie, Vaibhava Goel, Samuel Thomas	2014	36
17	Weak top-down constraints for unsupervised acoustic model training Aren Jansen, Samuel Thomas, Hynek Heřmanský	2013	36
18	Leveraging Unpaired Text Data for Training End-To-End Speech-to-Intent Systems Yinghui Huang, Hong-Kwang Jeff Kuo, Samuel Thomas, Zvi Kons, Kartik Audhkhasi, Brian Kingsbury, Ron Hoory, Michael Picheny	2020	35
19	Improvements to the IBM speech activity detection system for the DARPA RATS program Samuel Thomas, George Saon, Maarten Van Segbroeck, Shrikanth Narayanan	2015	35
20	Management and Characterization of Abiotic Stress via PhénoField®, a High-Throughput Field Phenotyping Platform Frontiers in Plant Science ·Katia Beauchêne, Fabien Leroy, Antoine Fournier, Céline Huet, Michel Bonnefoy, Josiane Lorgeou, Benoît de Solan, Benoît Piquemal, Samuel Thomas, Jean‐Pierre Cohan	2019	33

About Samuel Thomas

Samuel Thomas is a scholar working on Artificial Intelligence, Signal Processing, Computer Vision and Pattern Recognition, Plant Science and Ecology, having authored 110 papers that have together received 2.4k indexed citations. Recurring topics across this work include Speech Recognition and Synthesis (72 papers), Speech and Audio Processing (65 papers), Music and Audio Processing (53 papers), Natural Language Processing Techniques (14 papers), Speech and dialogue systems (12 papers), Topic Modeling (6 papers), Video Analysis and Summarization (5 papers) and Blind Source Separation Techniques (5 papers). The work is most often cited by research in Signal Processing (1.3k citations), Artificial Intelligence (1.7k citations), Environmental Engineering (205 citations), Computer Vision and Pattern Recognition (255 citations) and Ecology (253 citations). Samuel Thomas has collaborated with scholars based in United States, Germany and India. Frequent co-authors include Hynek Heřmanský, Sriram Ganapathy, George Saon, Richard C. Rose, Ondřej Glembek, Pinar Akyazi, Ariya Rastrow, Nagendra Kumar Goel, Lukáš Burget and Kai Feng. Their work appears in journals such as The Journal of the Acoustical Society of America, IEEE Signal Processing Letters, Frontiers in Plant Science, Potato Research and ISPRS Journal of Photogrammetry and Remote Sensing.

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