Anurag Kumar






A Closer Look at Weak Label Learning for Audio Events. [arXiv]
Ankit Shah*, Anurag Kumar*, Alex Hauptmann and Bhiksha Raj. (*Equal Contribution)

Large Scale Audio Event Classification using Weak Labels.
Anurag Kumar, Bhiksha Raj.
Poster at Speech and Audio in the Northeast (SANE) Workshop, 2017.

Unsupervised Fusion Weight Learning in Multiple Classifier Systems. [arXiv]
Anurag Kumar, Bhiksha Raj.

Features and Kernels for Audio Event Recognition. [arXiv]
Anurag Kumar, Bhiksha Raj.

Informedia@ Trecvid 2014: Multimedia Event Detection and Recounting. pdf
CMU Aladdin Team. (Best Performance Multimedia Event Detection at NIST TRECVID, 2014. )
NIST TRECVID Workshop, 2014.


A Sequential Self Teaching Approach for Improving Generalization in Sound Event Recognition. [arXiv]
Anurag Kumar, Vamsi Krishna Ithapu.
International Conference on Machine Learning (ICML), 2020.

Large Scale Audiovisual Learning of Sounds with Weakly Labeled Data. [arXiv]
Haytham M Fayek*, Anurag Kumar* (*Equal Contribution).
29th International Joint Conference on Artificial Intelligence (IJCAI), 2020.
New state-of-the-art on Audioset using audio and visual modalities.

SeCoST: Sequential Co-Supervision For Large Scale Weakly Labeled Audio Event Detection. [arXiv]
Anurag Kumar, Vamsi Krishna Ithapu.
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020.

Learning Sound Events from Webly Labeled Data. [arXiv]
Anurag Kumar, Ankit Shah, Alex Hauptmann and Bhiksha Raj.
28th International Joint Conference on Artificial Intelligence (IJCAI), 2019.
Companion Webpage with Additional Results. here.

Classifier Risk Estimation under Limited Labeling Resources. [arXiv]
Anurag Kumar, Bhiksha Raj.
22nd Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD), 2018.

Knowledge Transfer From Weakly Labeled Audio Using Convolutional Neural Network For Sound Events and Scenes. [arXiv]
Anurag Kumar, Maksim Khadkevich, Christian Fügen.
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018.
Set state-of-the-art results on Audioset and ESC-50 datasets. Companion Webpage here.

Content Based Representations Of Audio Using Siamese Neural Networks. [arXiv]
Pranay Manocha, Rohan Badlani, Anurag Kumar, Ankit Shah, Benjamin Elizalde, Bhiksha Raj.
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018.

Framework For Evaluation Of Sound Event Detection In Web Videos. [arXiv]
Rohan Badlani, Ankit Shah, Benjamin Elizalde, Anurag Kumar, Bhiksha Raj.
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018.

Deep CNN Framework for Audio Event Recognition using Weakly Labeled Web Data. [arXiv]
Anurag Kumar, Bhiksha Raj.
Neural Information Processing Systems (NIPS), Workshop on Machine Learning for Audio, 2017.

NELS: Never-Ending Learner of Sounds. [arXiv]
Benjamin Elizalde, Rohan Badlani, Ankit Shah, Anurag Kumar, Bhiksha Raj.
Neural Information Processing Systems (NIPS), Workshop on Machine Learning for Audio, 2017.

Audio Content based Geotagging in Multimedia. [arXiv]
Anurag Kumar, Benjamin Elizalde, Bhiksha Raj.
Interspeech, 2017.

Audio Event and Scene Recognition: A Unified Approach using Strongly and Weakly Labeled Data. [arXiv]
Anurag Kumar, Bhiksha Raj
IEEE International Joint Conference on Neural Networks (IJCNN), 2017.

Discovering Sound Concepts and Acoustic Relations In Text. [arXiv]
Anurag Kumar, Bhiksha Raj, Ndapandula Nakashole.
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2017.
Companion Webpage here.

An Approach for Self-Training Audio Event Detectors Using Web Data. [arXiv]
Ankit Shah, Rohan Badlani, Anurag Kumar, Benjamin Elizalde, Bhiksha Raj.
25th European Signal Processing Conference (EUSIPCO), 2017.

Experiments on the DCASE Challenge 2016: Acoustic Scene Classification and Sound Event Detection in Real Life Recording. [arXiv]
Benjamin Elizalde, Anurag Kumar, Ankit Shah, Rohan Badlani, Emmanuel Vincent, Bhiksha Raj.
Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE), 2016.

Weakly Supervised Scalable Audio Content Analysis. [arXiv]
Anurag Kumar, Bhiksha Raj.
IEEE International Conference on Multimedia & Expo (ICME), 2016.

Audio Event Detection using Weakly Labeled Data. [arXiv]
Anurag Kumar, Bhiksha Raj.
24th ACM International Conference on Multimedia (ACM Multimedia), 2016.
This paper introduced weakly supervised learning for the first time to the problem of sound event detection.

Speech Enhancement In Multiple-Noise Conditions using Deep Neural Networks. [arXiv]
Anurag Kumar, Dinei Florencio.
Interspeech, 2016.
Companion Webpage and enhancement audio samples are here .

A Novel Ranking Method For Multiple Classifier Systems. [IEEE Xplore]
Anurag Kumar, Bhiksha Raj.
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2015.

Detecting Sound Objects In Audio Recordings. [Eurasip]
Anurag Kumar, Rita Singh, Bhiksha Raj.
22nd European Signal Processing Conference (EUSIPCO), 2014.

Undergraduate Papers

Monaural Speaker Segregation Using Group Delay Spectral Matrix Factorization. [IEEE Xplore]
Karan Nathwani, Anurag Kumar and Rajesh Hegde.
20th National Conference on Communications (NCC), 2014.
Nominated for Best Paper Award.

Event Detection in Short Duration Audio Using Gaussian Mixture Model and Random Forest Classifier. [IEEE Xplore]
Anurag Kumar, Rajesh Hegde, Rita Singh and Bhiksha Raj.
21st European Signal Processing Conference (EUSIPCO), 2013.

Audio Event Detection from Acoustic Unit Occurrence Patterns. [IEEE Xplore]
Anurag Kumar, Pranay Dighe, Rita Singh, Sourish Chaudhuri and Bhiksha Raj.
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2012.




I have had my results for a long time, but I do not yet know how I am to arrive at them. - Carl Friedrich Gauss