Samuel Thomas

发表

Predictable accelerator design with time-sensitive affine types

Zhiru Zhang, Rachit Nigam, Sachille Atapattu, 2020, PLDI.

Natural sounding TTS based on syllable-like units

Hema A. Murthy, Samuel Thomas, M. Nageshwara Rao, 2006, 2006 14th European Signal Processing Conference.

Toward optimizing stream fusion in multistream recognition of speech.

Hynek Hermansky, Samuel Thomas, Nima Mesgarani, 2011, The Journal of the Acoustical Society of America.

Adaptive Stream Fusion in Multistream Recognition of Speech

Hynek Hermansky, Nima Mesgarani, Samuel Thomas, 2011, INTERSPEECH.

NATURAL SOUNDING TEXT-TO-SPEECH SYNTHESIS BASED ON SYLLABLE-LIKE UNITS

Samuel Thomas, Samuel Thomas, 2007 .

Intrinsic Spectral Analysis for Zero and High Resource Speech Recognition

Aren Jansen, Hynek Hermansky, Samuel Thomas, 2012, INTERSPEECH.

Design of a Virtual Reality Training System for Micro-robotic Cell Injection

Ben Horan, Samuel Thomas, Syafizwan Faroque, 2015 .

A novel estimation of feature-space MLLR for full-covariance models

Kai Feng, Ariya Rastrow, Lukás Burget, 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

Approaches to automatic lexicon learning with limited training examples

Kai Feng, Ariya Rastrow, Lukás Burget, 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

Training Spoken Language Understanding Systems with Non-Parallel Speech and Text

Mark Hasegawa-Johnson, Leda Sari, Samuel Thomas, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Compiling Constraint Networks into Multivalued Decomposable Decision Graphs

Jean-Marie Lagniez, Pierre Marquis, Samuel Thomas, 2015, IJCAI.

Comparison of modulation features for phoneme recognition

Hynek Hermansky, Samuel Thomas, Sriram Ganapathy, 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

Invariant Representations for Noisy Speech Recognition pdf

Bhuvana Ramabhadran, Yoshua Bengio, Dmitriy Serdyuk, 2016, ArXiv.

Feature extraction using 2-d autoregressive models for speaker recognition

Hynek Hermansky, Samuel Thomas, Sriram Ganapathy, 2012, Odyssey.

Multilingual Data Selection for Low Resource Speech Recognition

Brian Kingsbury, Bhuvana Ramabhadran, Jia Cui, 2016, INTERSPEECH.

Replication Package for Article: Predictable Accelerator Design with Time-Sensitive Affine types

Zhiru Zhang, Zhijing Li, Rachit Nigam, 2020, Artifact Digital Object Group.

Knowledge Compilation for Model Counting: Affine Decision Trees

Jean-Marie Lagniez, Pierre Marquis, Samuel Thomas, 2013, IJCAI.

Deep neural network features and semi-supervised training for low resource speech recognition

Kenneth Ward Church, Hynek Hermansky, Samuel Thomas, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

Grounding Spoken Words in Unlabeled Video

Michael Picheny, James R. Glass, Antonio Torralba, 2019, CVPR Workshops.

Robust spectro-temporal features based on autoregressive models of Hilbert envelopes

Hynek Hermansky, Samuel Thomas, Sriram Ganapathy, 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

Efficient Knowledge Distillation from an Ensemble of Teachers

Bhuvana Ramabhadran, Jia Cui, Takashi Fukuda, 2017, INTERSPEECH.

Data Augmentation Improves Recognition of Foreign Accented Speech

Bhuvana Ramabhadran, Andrew Rosenberg, Takashi Fukuda, 2018, INTERSPEECH.

Exploiting Discriminative Point Process Models for Spoken Term Detection

Aren Jansen, Samuel Thomas, Richard C. Rose, 2012, INTERSPEECH.

MLP Based Phoneme Detectors for Speech Recognition

Geoffrey Zweig, Hynek Hermansky, Patrick Nguyen, 2011 .

Inference and Prediction of Stock Returns using Multilevel Models

Samuel Thomas, Brice Green, Sam Thomas, 2019, SSRN Electronic Journal.

MLP based phoneme detectors for Automatic Speech Recognition

Geoffrey Zweig, Hynek Hermansky, Patrick Nguyen, 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Speech Recognition with Segmental Conditional Random Fields: Final Report from the 2010 JHU Summer Workshop

Geoffrey Zweig, Aren Jansen, Hynek Hermansky, 2010 .

SUBSPACE GAUSSIAN MIXTURE MODELS FOR SPEECH RECOGNITION

Kai Feng, Ariya Rastrow, Lukás Burget, 2009 .

Improvements to N-gram Language Model Using Text Generated from Neural Language Model

Masayuki Suzuki, Samuel Thomas, Nobuyasu Itoh, 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Language identification of person names using CF-IOF based weighing function

Ashish Verma, Samuel Thomas, 2007, INTERSPEECH.

The subspace Gaussian mixture model - A structured model for speech recognition

Kai Feng, Ariya Rastrow, Lukás Burget, 2011, Comput. Speech Lang..

SimplerVoice: A Key Message & Visual Description Generator System for Illiteracy pdf

Kush R. Varshney, Samuel Thomas, Anne E. Gattiker, 2018, ArXiv.

Deep Order Statistic Networks

Vaibhava Goel, Samuel Thomas, Steven J. Rennie, 2014, 2014 IEEE Spoken Language Technology Workshop (SLT).

AVLnet: Learning Audio-Visual Language Representations from Instructional Videos pdf

Brian Kingsbury, Michael Picheny, James Glass, 2020, ArXiv.

Weak top-down constraints for unsupervised acoustic model training

Aren Jansen, Hynek Hermansky, Samuel Thomas, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

Static and dynamic modulation spectrum for speech recognition

Hynek Hermansky, Samuel Thomas, Sriram Ganapathy, 2009, INTERSPEECH.

Tandem representations of spectral envelope and modulation frequency features for ASR

Hynek Hermansky, Samuel Thomas, Sriram Ganapathy, 2009, INTERSPEECH.

Using Skip Graphs for Increased NUMA Locality

Hammurabi Mendes, Samuel Thomas, Jonad Pulaj, 2020, 2020 IEEE 32nd International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD).

Developing a speaker identification system for the DARPA RATS project

Hynek Hermansky, Richard M. Schwartz, Sri Harish Reddy Mallidi, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

Front-end for far-field speech recognition based on frequency domain linear prediction

Hynek Hermansky, Samuel Thomas, Sriram Ganapathy, 2008, INTERSPEECH.

Data-driven Posterior Features for Low Resource Speech Recognition Applications

Aren Jansen, Hynek Hermansky, Samuel Thomas, 2012, INTERSPEECH.

Implicit Transfer of Privileged Acoustic Information in a Generalized Knowledge Distillation Framework

Takashi Fukuda, Samuel Thomas, 2020, INTERSPEECH.

End-to-End Spoken Language Understanding Using Transformer Networks and Self-Supervised Pre-Trained Features pdf

Brian Kingsbury, Samuel Thomas, Edmilson Morais, 2020, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Learning Hamiltonian Monte Carlo in R

Wanzhu Tu, Samuel Thomas, W. Tu, 2020, The American statistician.

Phoneme recognition using spectral envelope and modulation frequency features

Hynek Hermansky, Samuel Thomas, Sriram Ganapathy, 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.

Zoning information for Wallowa County, Oregon

Samuel Thomas, Dawn Smith, Dawn Smith, 2009 .

Effective joint training of denoising feature space transforms and Neural Network based acoustic models

Bhuvana Ramabhadran, Ryuki Tachibana, Osamu Ichikawa, 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

H amiltonian M onte C arlo

Wanzhu Tu, Samuel Thomas, W. Tu, 2020 .

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

Brian Kingsbury, Michael Picheny, Samuel Thomas, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Applications of signal analysis using autoregressive models for amplitude modulation

Petr Motlícek, Hynek Hermansky, Samuel Thomas, 2009, 2009 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics.

Data-driven neural network based feature front-ends for automatic speech recognition

Samuel Thomas, 2012 .

On the importance of event detection for ASR

George Saon, Michael Picheny, David Haws, 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Performance monitoring for robustness in automatic recognition of speechi

Hynek Hermansky, Nima Mesgarani, Samuel Thomas, 2011, MLSLP.

A multistream multiresolution framework for phoneme recognition

Hynek Hermansky, Nima Mesgarani, Samuel Thomas, 2010, INTERSPEECH.

Multilingual MLP features for low-resource LVCSR systems

Hynek Hermansky, Samuel Thomas, Sriram Ganapathy, 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Resource-Adaptive Deep Learning for Visual Speech Recognition

Samuel Thomas, Gerasimos Potamianos, Alexandros Koumparoulis, 2020, INTERSPEECH.

Emerging Global Trends in Advanced Manufacturing

Samuel Thomas, Bhavya Lal, Stephanie Shipp, 2012 .

A phoneme recognition framework based on auditory spectro-temporal receptive fields

Hynek Hermansky, Nima Mesgarani, Samuel Thomas, 2010, INTERSPEECH.

Geospatial depiction of watershed and drinking water for Enterprise, Oregon

Samuel Thomas, Dawn Smith, 2009 .

Incorporating Homomorphically Encrypted Data in Studies of Real-World Evidence to Support Expanded Approvals of Cancer Treatments

Hamed Abedtash, Samuel Thomas, Silvia Paddock, 2018 .

Acoustic and Data-driven Features for Robust Speech Activity Detection

Hynek Hermansky, Sri Harish Reddy Mallidi, Spyridon Matsoukas, 2012, INTERSPEECH.

Haptic Virtual Reality Training Environment for Micro-robotic Cell Injection

Ben Horan, Samuel Thomas, Syafizwan Faroque, 2014, AsiaHaptics.

Domain Adaptation of CNN Based Acoustic Models Under Limited Resource Settings

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

Layering Data Structures over Skip Graphs for Increased NUMA Locality

Hammurabi Mendes, Samuel Thomas, Samuel Thomas, 2019, PODC.

The IBM BOLT speech transcription system

George Saon, Hong-Kwang Jeff Kuo, Samuel Thomas, 2015, INTERSPEECH.

Hilbert Envelope Based Features for Far-Field Speech Recognition

Hynek Hermansky, Samuel Thomas, Sriram Ganapathy, 2008, MLMI.

Temporal envelope compensation for robust phoneme recognition using modulation spectrum.

Hynek Hermansky, Samuel Thomas, Sriram Ganapathy, 2010, The Journal of the Acoustical Society of America.

Hilbert envelope based spectro-temporal features for phoneme recognition in telephone speech

Hynek Hermansky, Samuel Thomas, Sriram Ganapathy, 2008, INTERSPEECH.

Spectro-temporal features for Automatic Speech Recognition using Linear Prediction in spectral domain

Hynek Hermansky, Samuel Thomas, Sriram Ganapathy, 2008, 2008 16th European Signal Processing Conference.

Recognition of Reverberant Speech Using Frequency Domain Linear Prediction

Hynek Hermansky, Samuel Thomas, Sriram Ganapathy, 2008, IEEE Signal Processing Letters.

Cross-lingual and multi-stream posterior features for low resource LVCSR systems

Hynek Hermansky, Samuel Thomas, Sriram Ganapathy, 2010, INTERSPEECH.

English Conversational Telephone Speech Recognition by Humans and Machines

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

Location of agricultural properties listed as "marginal" by 2009 Oregon House Bill 3326

Samuel Thomas, Dawn Smith, 2009 .

A Recorded Debating Dataset pdf

Shachar Mirkin, Michal Jacovi, Hong-Kwang Jeff Kuo, 2017, LREC.

Multilingual acoustic modeling for speech recognition based on subspace Gaussian Mixture Models

Kai Feng, Ariya Rastrow, Lukás Burget, 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

Annealed dropout training of deep networks

Vaibhava Goel, Samuel Thomas, Steven J. Rennie, 2014, 2014 IEEE Spoken Language Technology Workshop (SLT).

End-to-End Spoken Language Understanding Without Full Transcripts

Brian Kingsbury, Samuel Thomas, Zvi Kons, 2020, INTERSPEECH.

A summary of the 2012 JHU CLSP workshop on zero resource speech technologies and models of early language acquisition

Kenneth Ward Church, Florian Metze, Aren Jansen, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

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).

Temporal envelope subtraction for robust speech recognition using modulation spectrum

Hynek Hermansky, Samuel Thomas, Sriram Ganapathy, 2009, 2009 IEEE Workshop on Automatic Speech Recognition & Understanding.

CNMF-based acoustic features for noise-robust ASR

Shrikanth S. Narayanan, Colin Vaz, Dimitrios Dimitriadis, 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Inference-Invariant Transformation of Batch Normalization for Domain Adaptation of Acoustic Models

Masayuki Suzuki, Samuel Thomas, Gakuto Kurata, 2018, INTERSPEECH.

Investigating factor analysis features for deep neural networks in noisy speech recognition

Dimitrios Dimitriadis, Samuel Thomas, Steven J. Rennie, 2015, INTERSPEECH.

Adaptation transforms of auto-associative neural networks as features for speaker verification

Hynek Hermansky, Sri Harish Reddy Mallidi, Samuel Thomas, 2012, Odyssey.

Modulation frequency features for phoneme recognition in noisy speech.

Hynek Hermansky, Samuel Thomas, Sriram Ganapathy, 2009, The Journal of the Acoustical Society of America.

Audio-Assisted Image Inpainting for Talking Faces

Samuel Thomas, Gerasimos Potamianos, Alexandros Koumparoulis, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Understanding Unequal Gender Classification Accuracy from Face Images pdf

Brian Kingsbury, Kush R. Varshney, Aleksandra Mojsilovic, 2018, ArXiv.

An Investigation on the Use of i-Vectors for Robust ASR

Dimitrios Dimitriadis, Samuel Thomas, Sriram Ganapathy, 2016, INTERSPEECH.

Robust language identification using convolutional neural network features

Mohamed Kamal Omar, Shrikanth S. Narayanan, Maarten Van Segbroeck, 2014, INTERSPEECH.

Transliteration Based Data Augmentation for Training Multilingual ASR Acoustic Models in Low Resource Settings

Brian Kingsbury, Samuel Thomas, Kartik Audhkhasi, 2020, INTERSPEECH.

Rapid Evaluation of Speech Representations for Spoken Term Discovery

Aren Jansen, Hynek Hermansky, Michael A. Carlin, 2011, INTERSPEECH.