Search

Your search keyword '"Sathish Kumar P"' showing total 611 results
Start Over Author "Sathish Kumar P"
611 results on '"Sathish Kumar P"'

1. Empowering Low-Resource Language ASR via Large-Scale Pseudo Labeling

Author

Bhogale, Kaushal Santosh, Mehendale, Deovrat, Parasa, Niharika, G, Sathish Kumar Reddy, Javed, Tahir, Kumar, Pratyush, and Khapra, Mitesh M.

Subjects
Computer Science - Computation and Language, Computer Science - Sound, Electrical Engineering and Systems Science - Audio and Speech Processing
Abstract

In this study, we tackle the challenge of limited labeled data for low-resource languages in ASR, focusing on Hindi. Specifically, we explore pseudo-labeling, by proposing a generic framework combining multiple ideas from existing works. Our framework integrates multiple base models for transcription and evaluators for assessing audio-transcript pairs, resulting in robust pseudo-labeling for low resource languages. We validate our approach with a new benchmark, IndicYT, comprising diverse YouTube audio files from multiple content categories. Our findings show that augmenting pseudo labeled data from YouTube with existing training data leads to significant performance improvements on IndicYT, without affecting performance on out-of-domain benchmarks, demonstrating the efficacy of pseudo-labeled data in enhancing ASR capabilities for low-resource languages. The benchmark, code and models developed as a part of this work will be made publicly available.

Published
2024

15. High-$T_c$ Berezinskii-Kosterlitz-Thouless transition in 2D superconducting systems with coupled deep and quasi-flat electronic bands with van Hove singularities

Author

Paramasivam, Sathish Kumar, Gangadharan, Shakhil Ponnarassery, Milošević, Milorad V., and Perali, Andrea

Subjects
Condensed Matter - Superconductivity
Abstract

In the pursuit of higher critical temperature of superconductivity, quasi-flat electronic bands and van Hove singularities in two dimensions (2D) have emerged as a potential approach to enhance Cooper pairing on the basis of mean-field expectations. However, these special electronic features suppress the superfluid stiffness and, hence, the Berezinskii-Kosterlitz-Thouless (BKT) transition in 2D superconducting systems, leading to the emergence of a significant pseudogap regime due to superconducting fluctuations. In the strong-coupling regime, one finds that superfluid stiffness is inversely proportional to the superconducting gap, which is the predominant factor contributing to the strong suppression of superfluid stiffness. Here we reveal that the aforementioned limitation is avoided in a 2D superconducting electronic system with a quasi-flat electronic band with a strong pairing strength coupled to a deep band with weak electronic pairing strength. Owing to the multiband effects, we demonstrate a screening-like mechanism that circumvents the suppression of the superfluid stiffness. We report the optimal conditions for achieving a large enhancement of the BKT transition temperature and a substantial shrinking of the pseudogap regime by tuning the intraband couplings and the pair-exchange coupling between the two band-condensates.

Published
2023
Full Text
View/download PDF

49. Assessing Validity of Static Analysis Warnings using Ensemble Learning

Author

Tanwar, Anshul, Manikandan, Hariharan, Sundaresan, Krishna, Ganesan, Prasanna, Chandrasekaran, Sathish Kumar, and Ravi, Sriram

Subjects
Computer Science - Software Engineering, Computer Science - Machine Learning
Abstract

Static Analysis (SA) tools are used to identify potential weaknesses in code and fix them in advance, while the code is being developed. In legacy codebases with high complexity, these rules-based static analysis tools generally report a lot of false warnings along with the actual ones. Though the SA tools uncover many hidden bugs, they are lost in the volume of fake warnings reported. The developers expend large hours of time and effort in identifying the true warnings. Other than impacting the developer productivity, true bugs are also missed out due to this challenge. To address this problem, we propose a Machine Learning (ML)-based learning process that uses source codes, historic commit data, and classifier-ensembles to prioritize the True warnings from the given list of warnings. This tool is integrated into the development workflow to filter out the false warnings and prioritize actual bugs. We evaluated our approach on the networking C codes, from a large data pool of static analysis warnings reported by the tools. Time-to-time these warnings are addressed by the developers, labelling them as authentic bugs or fake alerts. The ML model is trained with full supervision over the code features. Our results confirm that applying deep learning over the traditional static analysis reports is an assuring approach for drastically reducing the false positive rates.

Published
2021

50. Multi-context Attention Fusion Neural Network for Software Vulnerability Identification

Author

Tanwar, Anshul, Manikandan, Hariharan, Sundaresan, Krishna, Ganesan, Prasanna, Chandrasekaran, Sathish Kumar, and Ravi, Sriram

Subjects
Computer Science - Artificial Intelligence, Computer Science - Software Engineering
Abstract

Security issues in shipped code can lead to unforeseen device malfunction, system crashes or malicious exploitation by crackers, post-deployment. These vulnerabilities incur a cost of repair and foremost risk the credibility of the company. It is rewarding when these issues are detected and fixed well ahead of time, before release. Common Weakness Estimation (CWE) is a nomenclature describing general vulnerability patterns observed in C code. In this work, we propose a deep learning model that learns to detect some of the common categories of security vulnerabilities in source code efficiently. The AI architecture is an Attention Fusion model, that combines the effectiveness of recurrent, convolutional and self-attention networks towards decoding the vulnerability hotspots in code. Utilizing the code AST structure, our model builds an accurate understanding of code semantics with a lot less learnable parameters. Besides a novel way of efficiently detecting code vulnerability, an additional novelty in this model is to exactly point to the code sections, which were deemed vulnerable by the model. Thus helping a developer to quickly focus on the vulnerable code sections; and this becomes the "explainable" part of the vulnerability detection. The proposed AI achieves 98.40% F1-score on specific CWEs from the benchmarked NIST SARD dataset and compares well with state of the art.

Published
2021

Catalog

Books, media, physical & digital resources
See catalog results