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

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Anurag Kumar

NICE-Beam: Neural Integrated Covariance Estimators for Time-Varying Beamformers


Dec 08, 2021
Jonah Casebeer, Jacob Donley, Daniel Wong, Buye Xu, Anurag Kumar


  Access Paper or Ask Questions

Conformer-Based Self-Supervised Learning for Non-Speech Audio Tasks


Nov 10, 2021
Sangeeta Srivastava, Yun Wang, Andros Tjandra, Anurag Kumar, Chunxi Liu, Kritika Singh, Yatharth Saraf

* 4 pages. Submitted to ICASSP in Oct 2021 

  Access Paper or Ask Questions

Multichannel Speech Enhancement without Beamforming


Oct 25, 2021
Asutosh Pandey, Buye Xu, Anurag Kumar, Jacob Donley, Paul Calamia, DeLiang Wang

* submitted to ICASSP 2022 

  Access Paper or Ask Questions

TADRN: Triple-Attentive Dual-Recurrent Network for Ad-hoc Array Multichannel Speech Enhancement


Oct 22, 2021
Ashutosh Pandey, Buye Xu, Anurag Kumar, Jacob Donley, Paul Calamia, DeLiang Wang

* submitted to ICASSP 2022 

  Access Paper or Ask Questions

TPARN: Triple-path Attentive Recurrent Network for Time-domain Multichannel Speech Enhancement


Oct 20, 2021
Ashutosh Pandey, Buye Xu, Anurag Kumar, Jacob Donley, Paul Calamia, DeLiang Wang

* submitted to ICASSP 2022 

  Access Paper or Ask Questions

Continual self-training with bootstrapped remixing for speech enhancement


Oct 19, 2021
Efthymios Tzinis, Yossi Adi, Vamsi K. Ithapu, Buye Xu, Anurag Kumar

* Submitted to ICASSP 2022 

  Access Paper or Ask Questions

Ego4D: Around the World in 3,000 Hours of Egocentric Video


Oct 13, 2021
Kristen Grauman, Andrew Westbury, Eugene Byrne, Zachary Chavis, Antonino Furnari, Rohit Girdhar, Jackson Hamburger, Hao Jiang, Miao Liu, Xingyu Liu, Miguel Martin, Tushar Nagarajan, Ilija Radosavovic, Santhosh Kumar Ramakrishnan, Fiona Ryan, Jayant Sharma, Michael Wray, Mengmeng Xu, Eric Zhongcong Xu, Chen Zhao, Siddhant Bansal, Dhruv Batra, Vincent Cartillier, Sean Crane, Tien Do, Morrie Doulaty, Akshay Erapalli, Christoph Feichtenhofer, Adriano Fragomeni, Qichen Fu, Christian Fuegen, Abrham Gebreselasie, Cristina Gonzalez, James Hillis, Xuhua Huang, Yifei Huang, Wenqi Jia, Weslie Khoo, Jachym Kolar, Satwik Kottur, Anurag Kumar, Federico Landini, Chao Li, Yanghao Li, Zhenqiang Li, Karttikeya Mangalam, Raghava Modhugu, Jonathan Munro, Tullie Murrell, Takumi Nishiyasu, Will Price, Paola Ruiz Puentes, Merey Ramazanova, Leda Sari, Kiran Somasundaram, Audrey Southerland, Yusuke Sugano, Ruijie Tao, Minh Vo, Yuchen Wang, Xindi Wu, Takuma Yagi, Yunyi Zhu, Pablo Arbelaez, David Crandall, Dima Damen, Giovanni Maria Farinella, Bernard Ghanem, Vamsi Krishna Ithapu, C. V. Jawahar, Hanbyul Joo, Kris Kitani, Haizhou Li, Richard Newcombe, Aude Oliva, Hyun Soo Park, James M. Rehg, Yoichi Sato, Jianbo Shi, Mike Zheng Shou, Antonio Torralba, Lorenzo Torresani, Mingfei Yan, Jitendra Malik


  Access Paper or Ask Questions

Incorporating Real-world Noisy Speech in Neural-network-based Speech Enhancement Systems


Sep 21, 2021
Yangyang Xia, Buye Xu, Anurag Kumar


  Access Paper or Ask Questions

NORESQA -- A Framework for Speech Quality Assessment using Non-Matching References


Sep 16, 2021
Pranay Manocha, Buye Xu, Anurag Kumar


  Access Paper or Ask Questions

Online Self-Attentive Gated RNNs for Real-Time Speaker Separation


Jul 27, 2021
Ori Kabeli, Yossi Adi, Zhenyu Tang, Buye Xu, Anurag Kumar

* Appears at the Workshop on Machine Learning in Speech and Language Processing 2021 

  Access Paper or Ask Questions

Do sound event representations generalize to other audio tasks? A case study in audio transfer learning


Jun 21, 2021
Anurag Kumar, Yun Wang, Vamsi Krishna Ithapu, Christian Fuegen

* Accepted Interspeech 2021 

  Access Paper or Ask Questions

DPLM: A Deep Perceptual Spatial-Audio Localization Metric


May 29, 2021
Pranay Manocha, Anurag Kumar, Buye Xu, Anjali Menon, Israel D. Gebru, Vamsi K. Ithapu, Paul Calamia


  Access Paper or Ask Questions

Decentralized, Hybrid MAC Design with Reduced State Information Exchange for Low-Delay IoT Applications


May 24, 2021
Avinash Mohan, Arpan Chattopadhyay, Shivam Vinayak Vatsa, Anurag Kumar

* 56 pages, 20 figures 

  Access Paper or Ask Questions

Multi-Channel Speech Enhancement using Graph Neural Networks


Feb 13, 2021
Panagiotis Tzirakis, Anurag Kumar, Jacob Donley

* Proc. ICASSP 2021 

  Access Paper or Ask Questions

A bandit approach to curriculum generation for automatic speech recognition


Feb 06, 2021
Anastasia Kuznetsova, Anurag Kumar, Francis M. Tyers


  Access Paper or Ask Questions

A Sequential Self Teaching Approach for Improving Generalization in Sound Event Recognition


Jun 30, 2020
Anurag Kumar, Vamsi Krishna Ithapu

* Accepted International Conference on Machine Learning $\textbf{(ICML) 2020}$. 14 pages 

  Access Paper or Ask Questions

Large Scale Audiovisual Learning of Sounds with Weakly Labeled Data


May 29, 2020
Haytham M. Fayek, Anurag Kumar

* 29th International Joint Conference on Artificial Intelligence (IJCAI 2020) 

  Access Paper or Ask Questions

SeCoST: Sequential Co-Supervision for Weakly Labeled Audio Event Detection


Oct 25, 2019
Anurag Kumar, Vamsi Krishna Ithapu


  Access Paper or Ask Questions

A Closer Look at Weak Label Learning for Audio Events


Apr 24, 2018
Ankit Shah, Anurag Kumar, Alexander G. Hauptmann, Bhiksha Raj

* 10 pages 

  Access Paper or Ask Questions

Framework for evaluation of sound event detection in web videos


Apr 04, 2018
Rohan Badlani, Ankit Shah, Benjamin Elizalde, Anurag Kumar, Bhiksha Raj

* Camera Ready Version of Paper accepted at International Conference on Acoustics, Speech, and Signal Processing (ICASSP) 2018. First two Authors - Rohan Badlani and Ankit Shah contributed equally 

  Access Paper or Ask Questions

Classifier Risk Estimation under Limited Labeling Resources


Feb 19, 2018
Anurag Kumar, Bhiksha Raj

* PAKDD 2018 

  Access Paper or Ask Questions

Deep CNN Framework for Audio Event Recognition using Weakly Labeled Web Data


Jul 20, 2017
Anurag Kumar, Bhiksha Raj


  Access Paper or Ask Questions

An Approach for Self-Training Audio Event Detectors Using Web Data


Jun 27, 2017
Benjamin Elizalde, Ankit Shah, Siddharth Dalmia, Min Hun Lee, Rohan Badlani, Anurag Kumar, Bhiksha Raj, Ian Lane

* 5 pages 

  Access Paper or Ask Questions

Audio Event and Scene Recognition: A Unified Approach using Strongly and Weakly Labeled Data


Feb 18, 2017
Anurag Kumar, Bhiksha Raj

* IJCNN 2017, 8 pages 

  Access Paper or Ask Questions

Discovering Sound Concepts and Acoustic Relations In Text


Feb 13, 2017
Anurag Kumar, Bhiksha Raj, Ndapandula Nakashole

* ICASSP 2017 

  Access Paper or Ask Questions

Audio Event Detection using Weakly Labeled Data


Jul 06, 2016
Anurag Kumar, Bhiksha Raj

* ACM Multimedia 2016 

  Access Paper or Ask Questions

Weakly Supervised Scalable Audio Content Analysis


Jun 12, 2016
Anurag Kumar, Bhiksha Raj

* ICME 2016 

  Access Paper or Ask Questions

Unsupervised Fusion Weight Learning in Multiple Classifier Systems


Feb 06, 2015
Anurag Kumar, Bhiksha Raj


  Access Paper or Ask Questions