Samuel Thomas

发表

Mixture of Auto-Associative Neural Networks for Speaker Verification

Hynek Hermansky, Garimella S. V. S. Sivaram, Samuel Thomas, 2011, INTERSPEECH.

Learning Speaker Aware Offsets for Speaker Adaptation of Neural Networks

Mark Hasegawa-Johnson, Samuel Thomas, Leda Sari, 2019, INTERSPEECH.

Geospatial depiction of land owners who have filed Measure 37 claims within Wallowa County, Oregon

Samuel Thomas, Dawn Smith, 2009 .

The UMD-JHU 2011 speaker recognition system

Sridhar Krishna Nemala, Mounya Elhilali, Hynek Hermansky, 2012, 2012 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).

Joint Modeling of Accents and Acoustics for Multi-Accent Speech Recognition

Bhuvana Ramabhadran, Mark Hasegawa-Johnson, Andrew Rosenberg, 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Detection and Recovery of OOVs for Improved English Broadcast News Captioning

Michael Picheny, Samuel Thomas, Kartik Audhkhasi, 2019, INTERSPEECH.

Pre-training of Speaker Embeddings for Low-latency Speaker Change Detection in Broadcast News

Michael Picheny, Mark Hasegawa-Johnson, Samuel Thomas, 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Speech recognitionwith segmental conditional random fields: A summary of the JHU CLSP 2010 Summer Workshop

Geoffrey Zweig, Les E. Atlas, Aren Jansen, 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Proof-of-concept study: Homomorphically encrypted data can support real-time learning in personalized cancer medicine

Hamed Abedtash, Samuel Thomas, Silvia Paddock, 2019, BMC Medical Informatics and Decision Making.

Resource-efficient TDNN Architectures for Audio-visual Speech Recognition

Gerasimos Potamianos, Samuel Thomas, Alexandros Koumparoulis, 2021, 2021 29th European Signal Processing Conference (EUSIPCO).

Multimodal Clustering Networks for Self-supervised Learning from Unlabeled Videos pdf

James Glass, Brian Kingsbury, Michael Picheny, 2021, 2021 IEEE/CVF International Conference on Computer Vision (ICCV).

Cascaded Multilingual Audio-Visual Learning from Videos pdf

James Glass, Brian Kingsbury, Michael Picheny, 2021, Interspeech.

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

James Glass, Brian Kingsbury, Michael Picheny, 2021, Interspeech 2021.

Speak or Chat with Me: End-to-End Spoken Language Understanding System with Flexible Inputs pdf

Michael Picheny, Samuel Thomas, Edmilson Morais, 2021, Interspeech.

Knowledge Distillation Based Training of Universal ASR Source Models for Cross-Lingual Transfer

Samuel Thomas, Takashi Fukuda, 2021, Interspeech 2021.

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

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

RNN Transducer Models for Spoken Language Understanding

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

Text-to-Speech Synthesis using syllable-like units

Hema A. Murthy, T. Nagarajan, Samuel Thomas, .

Design and Development of a Text-To-Speech Synthesizer for Indian Languages

Hema A Murthy, Samuel Thomas, Kartik Bommepally, .

Speaker Adaptation of Neural Networks with Learning Speaker Aware Offsets

Michael Picheny, Mark Hasegawa-Johnson, Samuel Thomas, 2019 .

Low Development Cost , High Quality Speech Recognition for New Languages and Domains ” : Report from 2009 Johns Hopkins / CLSP Summer Workshop

Ariya Rastrow, Daniel Povey, Martin Karafiát, 2009 .

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).