Search Results for author: Deepak Mittal

Found 10 papers, 4 papers with code

Svadhyaya system for the Second Diagnosing COVID-19 using Acoustics Challenge 2021

no code implementations11 Jun 2022 Deepak Mittal, Amir H. Poorjam, Debottam Dutta, Debarpan Bhattacharya, Zemin Yu, Sriram Ganapathy, Maneesh Singh

This report describes the system used for detecting COVID-19 positives using three different acoustic modalities, namely speech, breathing, and cough in the second DiCOVA challenge.

SpliceOut: A Simple and Efficient Audio Augmentation Method

no code implementations30 Sep 2021 Arjit Jain, Pranay Reddy Samala, Deepak Mittal, Preethi Jyoti, Maneesh Singh

Time masking has become a de facto augmentation technique for speech and audio tasks, including automatic speech recognition (ASR) and audio classification, most notably as a part of SpecAugment.

Audio Classification Automatic Speech Recognition +4

ProAlignNet : Unsupervised Learning for Progressively Aligning Noisy Contours

no code implementations23 May 2020 VSR Veeravasarapu, Abhishek Goel, Deepak Mittal, Maneesh Singh

Contour shape alignment is a fundamental but challenging problem in computer vision, especially when the observations are partial, noisy, and largely misaligned.

Studying the Plasticity in Deep Convolutional Neural Networks using Random Pruning

1 code implementation26 Dec 2018 Deepak Mittal, Shweta Bhardwaj, Mitesh M. Khapra, Balaraman Ravindran

In this work, we report experiments which suggest that the comparable performance of the pruned network is not due to the specific criterion chosen but due to the inherent plasticity of deep neural networks which allows them to recover from the loss of pruned filters once the rest of the filters are fine-tuned.

Image Classification Image Segmentation +3

Recovering from Random Pruning: On the Plasticity of Deep Convolutional Neural Networks

1 code implementation31 Jan 2018 Deepak Mittal, Shweta Bhardwaj, Mitesh M. Khapra, Balaraman Ravindran

In this work, we report experiments which suggest that the comparable performance of the pruned network is not due to the specific criterion chosen but due to the inherent plasticity of deep neural networks which allows them to recover from the loss of pruned filters once the rest of the filters are fine-tuned.

Image Classification object-detection +1

Cannot find the paper you are looking for? You can Submit a new open access paper.