Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Sanjeev Khudanpur

Sanjeev Khudanpur

Reformulating DOVER-Lap Label Mapping as a Graph Partitioning Problem

Apr 05, 2021
Desh Raj, Sanjeev Khudanpur

Figure 1 for Reformulating DOVER-Lap Label Mapping as a Graph Partitioning Problem

Figure 2 for Reformulating DOVER-Lap Label Mapping as a Graph Partitioning Problem

Figure 3 for Reformulating DOVER-Lap Label Mapping as a Graph Partitioning Problem

Figure 4 for Reformulating DOVER-Lap Label Mapping as a Graph Partitioning Problem

* 5 pages, 3 figures. Submitted to INTERSPEECH 2021

Access Paper or Ask Questions

Adversarial Attacks and Defenses for Speech Recognition Systems

Mar 31, 2021
Piotr Żelasko, Sonal Joshi, Yiwen Shao, Jesus Villalba, Jan Trmal, Najim Dehak, Sanjeev Khudanpur

Figure 1 for Adversarial Attacks and Defenses for Speech Recognition Systems

* This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible

Access Paper or Ask Questions

An Asynchronous WFST-Based Decoder For Automatic Speech Recognition

Mar 16, 2021
Hang Lv, Zhehuai Chen, Hainan Xu, Daniel Povey, Lei Xie, Sanjeev Khudanpur

Figure 1 for An Asynchronous WFST-Based Decoder For Automatic Speech Recognition

Figure 2 for An Asynchronous WFST-Based Decoder For Automatic Speech Recognition

Figure 3 for An Asynchronous WFST-Based Decoder For Automatic Speech Recognition

Figure 4 for An Asynchronous WFST-Based Decoder For Automatic Speech Recognition

* 5 pages, 5 figures, icassp

Access Paper or Ask Questions

Learning Feature Weights using Reward Modeling for Denoising Parallel Corpora

Mar 11, 2021
Gaurav Kumar, Philipp Koehn, Sanjeev Khudanpur

Figure 1 for Learning Feature Weights using Reward Modeling for Denoising Parallel Corpora

Figure 2 for Learning Feature Weights using Reward Modeling for Denoising Parallel Corpora

Figure 3 for Learning Feature Weights using Reward Modeling for Denoising Parallel Corpora

Figure 4 for Learning Feature Weights using Reward Modeling for Denoising Parallel Corpora

* 10 pages, 2 figures

Access Paper or Ask Questions

Learning Policies for Multilingual Training of Neural Machine Translation Systems

Mar 11, 2021
Gaurav Kumar, Philipp Koehn, Sanjeev Khudanpur

Figure 1 for Learning Policies for Multilingual Training of Neural Machine Translation Systems

Figure 2 for Learning Policies for Multilingual Training of Neural Machine Translation Systems

Figure 3 for Learning Policies for Multilingual Training of Neural Machine Translation Systems

Figure 4 for Learning Policies for Multilingual Training of Neural Machine Translation Systems

* 7 pages, 2 figures

Access Paper or Ask Questions

A Parallelizable Lattice Rescoring Strategy with Neural Language Models

Mar 08, 2021
Ke Li, Daniel Povey, Sanjeev Khudanpur

Figure 1 for A Parallelizable Lattice Rescoring Strategy with Neural Language Models

Figure 2 for A Parallelizable Lattice Rescoring Strategy with Neural Language Models

Figure 3 for A Parallelizable Lattice Rescoring Strategy with Neural Language Models

Figure 4 for A Parallelizable Lattice Rescoring Strategy with Neural Language Models

* To appear at ICASSP 2021. 5 pages, 1 figure

Access Paper or Ask Questions

Wake Word Detection with Streaming Transformers

Feb 08, 2021
Yiming Wang, Hang Lv, Daniel Povey, Lei Xie, Sanjeev Khudanpur

Figure 1 for Wake Word Detection with Streaming Transformers

Figure 2 for Wake Word Detection with Streaming Transformers

Figure 3 for Wake Word Detection with Streaming Transformers

Figure 4 for Wake Word Detection with Streaming Transformers

* Accepted at IEEE ICASSP 2021. 5 pages, 3 figures

Access Paper or Ask Questions

Fine-grained activity recognition for assembly videos

Dec 02, 2020
Jonathan D. Jones, Cathryn Cortesa, Amy Shelton, Barbara Landau, Sanjeev Khudanpur, Gregory D. Hager

Figure 1 for Fine-grained activity recognition for assembly videos

Figure 2 for Fine-grained activity recognition for assembly videos

Figure 3 for Fine-grained activity recognition for assembly videos

Figure 4 for Fine-grained activity recognition for assembly videos

* 8 pages, 6 figures. Submitted to RA-L/ICRA 2021

Access Paper or Ask Questions