activity
20172022
most citedDARVIZ: Deep Abstract Representation, Visualization, and Verification of Deep Learning Models

17 citations · 36 across the 7 of their papers we have counts for

collaborators

11 papers

cs.CL2022

Adaptive Discounting of Implicit Language Models in RNN-Transducers

Vinit Unni, Shreya Khare, Ashish Mittal +3

RNN-Transducer (RNN-T) models have become synonymous with streaming end-to-end ASR systems. While they perform competitively on a number of evaluation categories, rare words pose a…

cs.CL20219 cited

Representation based meta-learning for few-shot spoken intent recognition

Ashish Mittal, Samarth Bharadwaj, Shreya Khare +3

Spoken intent detection has become a popular approach to interface with various smart devices with ease. However, such systems are limited to the preset list of intents-terms or co…

cs.CL2021

Multilingual and code-switching ASR challenges for low resource Indian languages

Anuj Diwan, Rakesh Vaideeswaran, Sanket Shah +19

Recently, there is increasing interest in multilingual automatic speech recognition (ASR) where a speech recognition system caters to multiple low resource languages by taking adva…

cs.AI20202 cited

Adversarial Black-Box Attacks On Text Classifiers Using Multi-Objective Genetic Optimization Guided By Deep Networks

Alex Mathai, Shreya Khare, Srikanth Tamilselvam +1

We propose a novel genetic-algorithm technique that generates black-box adversarial examples which successfully fool neural network based text classifiers. We perform a genetic sea…

cs.CL20201 cited

Benchmarking Popular Classification Models' Robustness to Random and Targeted Corruptions

Utkarsh Desai, Srikanth Tamilselvam, Jassimran Kaur +2

Text classification models, especially neural networks based models, have reached very high accuracy on many popular benchmark datasets. Yet, such models when deployed in real worl…

cs.HC2019

A Visual Programming Paradigm for Abstract Deep Learning Model Development

Srikanth Tamilselvam, Naveen Panwar, Shreya Khare +3

Deep learning is one of the fastest growing technologies in computer science with a plethora of applications. But this unprecedented growth has so far been limited to the consumpti…