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

Low Resource Multi-modal Data Augmentation for End-to-end ASR

Dec 10, 2018
Matthew Wiesner, Adithya Renduchintala, Shinji Watanabe, Chunxi Liu, Najim Dehak, Sanjeev Khudanpur

Figure 1 for Low Resource Multi-modal Data Augmentation for End-to-end ASR

Figure 2 for Low Resource Multi-modal Data Augmentation for End-to-end ASR

Figure 3 for Low Resource Multi-modal Data Augmentation for End-to-end ASR

Figure 4 for Low Resource Multi-modal Data Augmentation for End-to-end ASR

* 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

Building Corpora for Single-Channel Speech Separation Across Multiple Domains

Nov 06, 2018
Matthew Maciejewski, Gregory Sell, Leibny Paola Garcia-Perera, Shinji Watanabe, Sanjeev Khudanpur

Figure 1 for Building Corpora for Single-Channel Speech Separation Across Multiple Domains

Figure 2 for Building Corpora for Single-Channel Speech Separation Across Multiple Domains

* 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

Low-Resource Contextual Topic Identification on Speech

Sep 28, 2018
Chunxi Liu, Matthew Wiesner, Shinji Watanabe, Craig Harman, Jan Trmal, Najim Dehak, Sanjeev Khudanpur

Figure 1 for Low-Resource Contextual Topic Identification on Speech

Figure 2 for Low-Resource Contextual Topic Identification on Speech

Figure 3 for Low-Resource Contextual Topic Identification on Speech

Figure 4 for Low-Resource Contextual Topic Identification on Speech

* Accepted for publication at 2018 IEEE Workshop on Spoken Language Technology (SLT)

Access Paper or Ask Questions

A GPU-based WFST Decoder with Exact Lattice Generation

Jul 27, 2018
Zhehuai Chen, Justin Luitjens, Hainan Xu, Yiming Wang, Daniel Povey, Sanjeev Khudanpur

Figure 1 for A GPU-based WFST Decoder with Exact Lattice Generation

Figure 2 for A GPU-based WFST Decoder with Exact Lattice Generation

Figure 3 for A GPU-based WFST Decoder with Exact Lattice Generation

Figure 4 for A GPU-based WFST Decoder with Exact Lattice Generation

* accepted by INTERSPEECH 2018

Access Paper or Ask Questions

Automatic Speech Recognition and Topic Identification for Almost-Zero-Resource Languages

Jun 18, 2018
Matthew Wiesner, Chunxi Liu, Lucas Ondel, Craig Harman, Vimal Manohar, Jan Trmal, Zhongqiang Huang, Najim Dehak, Sanjeev Khudanpur

Figure 1 for Automatic Speech Recognition and Topic Identification for Almost-Zero-Resource Languages

Figure 2 for Automatic Speech Recognition and Topic Identification for Almost-Zero-Resource Languages

Figure 3 for Automatic Speech Recognition and Topic Identification for Almost-Zero-Resource Languages

Figure 4 for Automatic Speech Recognition and Topic Identification for Almost-Zero-Resource Languages

* Accepted for publication at Interspeech 2018

Access Paper or Ask Questions

Topic Identification for Speech without ASR

Jul 11, 2017
Chunxi Liu, Jan Trmal, Matthew Wiesner, Craig Harman, Sanjeev Khudanpur

Figure 1 for Topic Identification for Speech without ASR

Figure 2 for Topic Identification for Speech without ASR

Figure 3 for Topic Identification for Speech without ASR

* 5 pages, 2 figures; accepted for publication at Interspeech 2017

Access Paper or Ask Questions

An Empirical Evaluation of Zero Resource Acoustic Unit Discovery

Feb 05, 2017
Chunxi Liu, Jinyi Yang, Ming Sun, Santosh Kesiraju, Alena Rott, Lucas Ondel, Pegah Ghahremani, Najim Dehak, Lukas Burget, Sanjeev Khudanpur

Figure 1 for An Empirical Evaluation of Zero Resource Acoustic Unit Discovery

Figure 2 for An Empirical Evaluation of Zero Resource Acoustic Unit Discovery

* 5 pages, 1 figure; Accepted for publication at ICASSP 2017

Access Paper or Ask Questions