Ankit Shah

Orcid: 0000-0002-8838-5421

Affiliations:
  • Carnegie Mellon University, Language Technologies Institute, Pittsburgh, USA


According to our database1, Ankit Shah authored at least 20 papers between 2016 and 2023.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2023
Psychoacoustic Challenges Of Speech Enhancement On VoIP Platforms.
CoRR, 2023

LoFT: Local Proxy Fine-tuning For Improving Transferability Of Adversarial Attacks Against Large Language Model.
CoRR, 2023

Understanding and Mitigating the Label Noise in Pre-training on Downstream Tasks.
CoRR, 2023

Importance of negative sampling in weak label learning.
CoRR, 2023

Imprecise Label Learning: A Unified Framework for Learning with Various Imprecise Label Configurations.
CoRR, 2023

Improving Perceptual Quality, Intelligibility, and Acoustics on VoIP Platforms.
CoRR, 2023

Approach to Learning Generalized Audio Representation Through Batch Embedding Covariance Regularization and Constant-Q Transforms.
CoRR, 2023

An Approach to Ontological Learning from Weak Labels.
Proceedings of the IEEE International Conference on Acoustics, 2023

2022
On the pragmatism of using binary classifiers over data intensive neural network classifiers for detection of COVID-19 from voice.
CoRR, 2022

Ontological Learning from Weak Labels.
CoRR, 2022

2021
Training image classifiers using Semi-Weak Label Data.
CoRR, 2021

2019
Learning Sound Events from Webly Labeled Data.
Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, 2019

2018
A Closer Look at Weak Label Learning for Audio Events.
CoRR, 2018

NELS - Never-Ending Learner of Sounds.
CoRR, 2018

Content-Based Representations of Audio Using Siamese Neural Networks.
Proceedings of the 2018 IEEE International Conference on Acoustics, 2018

Framework for Evaluation of Sound Event Detection in Web Videos.
Proceedings of the 2018 IEEE International Conference on Acoustics, 2018

2017
An approach for self-training audio event detectors using web data.
Proceedings of the 25th European Signal Processing Conference, 2017

DCASE2017 Challenge Setup: Tasks, Datasets and Baseline System.
Proceedings of the Workshop on Detection and Classification of Acoustic Scenes and Events, 2017

2016
An Approach for Self-Training Audio Event Detectors Using Web Data.
CoRR, 2016

Experiments on the DCASE Challenge 2016: Acoustic Scene Classification and Sound Event Detection in Real Life Recording.
Proceedings of the Workshop on Detection and Classification of Acoustic Scenes and Events, 2016


  Loading...