Scott Novotney

According to our database, Scott Novotney authored at least 16 papers between 2009 and 2022.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2022

CUE Vectors: Modular Training of Language Models Conditioned on Diverse Contextual Signals.

Scott Novotney, Sreeparna Mukherjee, Zeeshan Ahmed, Andreas Stolcke

Proceedings of the Findings of the Association for Computational Linguistics: ACL 2022, 2022

2021

Adjunct-Emeritus Distillation for Semi-Supervised Language Model Adaptation.

Scott Novotney, Yile Gu, Ivan Bulyko

Proceedings of the 22nd Annual Conference of the International Speech Communication Association, Interspeech 2021, Brno, Czechia, August 30, 2021

Attention-based Contextual Language Model Adaptation for Speech Recognition.

Richard Diehl Martinez, Scott Novotney, Ivan Bulyko, Ariya Rastrow, Andreas Stolcke, Ankur Gandhe

Proceedings of the Findings of the Association for Computational Linguistics: ACL/IJCNLP 2021, 2021

2020

Improving accuracy of rare words for RNN-Transducer through unigram shallow fusion.

Vijay Ravi, Yile Gu, Ankur Gandhe, Ariya Rastrow, Linda Liu, Denis Filimonov, Scott Novotney, Ivan Bulyko

CoRR, 2020

2019

Hyperparameter Optimization of Topological Features for Machine Learning Applications.

Francis C. Motta, John Harer, Nick Leiby, Franco Marinozzi, Scott Novotney, Gabe Rocklin, Jed Singer, Devin Strickland, Matt Vaughn, Christopher J. Tralie, Rossella Bedini, Fabiano Bini, Gilberto Bini, Hamed Eramian, Marcio Gameiro, Steven B. Haase, Hugh Haddox

Proceedings of the 18th IEEE International Conference On Machine Learning And Applications, 2019

Robust keystroke transcription from the acoustic side-channel.

David Slater, Scott Novotney, Jessica Moore, Sean Morgan, Scott Tenaglia

Proceedings of the 35th Annual Computer Security Applications Conference, 2019

2016

Getting more from automatic transcripts for semi-supervised language modeling.

Scott Novotney, Richard M. Schwartz, Sanjeev Khudanpur

Comput. Speech Lang., 2016

BBN technologies' OpenSAD system.

Scott Novotney, Damianos G. Karakos, Jan Silovský, Richard M. Schwartz

Proceedings of the 2016 IEEE Spoken Language Technology Workshop, 2016

Model Adaptation and Active Learning in the BBN Speech Activity Detection System for the DARPA RATS Program.

Damianos G. Karakos, Scott Novotney, Le Zhang, Richard M. Schwartz

Proceedings of the 17th Annual Conference of the International Speech Communication Association, 2016

2015

Incorporating user feedback to re-rank keyword search results.

Scott Novotney, Kevin Jett, Owen Kimball

Proceedings of the 2015 IEEE Workshop on Automatic Speech Recognition and Understanding, 2015

2012

Semi-Supervised Methods for Improving Keyword Search of Unseen Terms.

Scott Novotney, Ivan Bulyko, Richard M. Schwartz, Sanjeev Khudanpur, Owen Kimball

Proceedings of the 13th Annual Conference of the International Speech Communication Association, 2012

2011

Unsupervised Arabic Dialect Adaptation with Self-Training.

Scott Novotney, Richard M. Schwartz, Sanjeev Khudanpur

Proceedings of the 12th Annual Conference of the International Speech Communication Association, 2011

2010

Crowdsourced Accessibility: Elicitation of Wikipedia Articles.

Scott Novotney, Chris Callison-Burch

Proceedings of the 2010 Workshop on Creating Speech and Language Data with Amazon's Mechanical Turk, 2010

Cheap, Fast and Good Enough: Automatic Speech Recognition with Non-Expert Transcription.

Scott Novotney, Chris Callison-Burch

Proceedings of the Human Language Technologies: Conference of the North American Chapter of the Association of Computational Linguistics, 2010

2009

Analysis of low-resource acoustic model self-training.

Scott Novotney, Richard M. Schwartz

Proceedings of the 10th Annual Conference of the International Speech Communication Association, 2009

Unsupervised acoustic and language model training with small amounts of labelled data.

Scott Novotney, Richard M. Schwartz, Jeff Z. Ma

Proceedings of the IEEE International Conference on Acoustics, 2009