Snehal Chaudhari

Snehal Chaudhari

SDE @ Avaya, M.S. in Computer Science @ Arizona State University

Posts by Collection

portfolio

publications

Software Engineer

Avaya, July 20, 2020 - July 08, 2022

  • Contributed in the development of multiple features of IP Office telephony system wherein specifically worked on call-media management, administration, and system monitoring features for on-premise and subscription models.
  • Contributed significantly to the integration of a standalone telephony app with Microsoft Teams for softphones, and call-control capabilities.
  • Responsible for building a cross-platform mobile application using the flutter framework along with core telephony services to improve user engagement, accessibility, and administrative experience.
  • Managed streamlining of real-time diagnostics log-management feature for backup and restore activities within multiple clusters. These projects allowed me to cater to large-scale problems and apply my skills in designing architecture to establish communication channels within a product ecosystem.

Graduate Research Assistant

Arizona State University, August 01, 2023 - May 06, 2024

  • Collaborated with MLCommons and NASA Harvest to design globally diverse benchmarking datasets for crop field boundaries using DataPerf standards.
  • Designed a pipeline for creating and matching stratified samples of crop parcels to standardized EO images, including download, conversion, and patchlet sampling.
  • Optimized cross-validation performance on boundaries with K-fold splits based on morphological characteristics.
  • Evaluated baseline models MaskRCNN, Segment Anything Model (SAM), and UNET to improve a benchmarking accuracy for sparse crop field annotations.

talks

Interactive Fractal Curve

Published:

  • This is a personal project which focuses on integrating some concepts of fractal geometry with D3.js. This project is still in progress.

PICT CSI Web Portal

Published:

  • Built a web portal for the management and registration of various events and activities of the CSI student branch, which affected 1.1k+ participants.
  • For end users, the portal offers insights into all event updates and news feeds, and for administrators, it presents a graphical representation of the distributions of various entities and membership statistics.

Generating Realistic Voices

Published:

  • Constructed a deep neural network-based model for language processing and regeneration that made AI-based voices indistinguishable from natural speech by capturing the distinct voice feature to perform TTS on constrained inputs.
  • Optimized language processing model with MelNet and WaveNet to retain linguistic information of multiple speakers.
  • Achieved accuracy of 86.2% using sequence-to-sequence recurrent network (Tacotron 2) along with modified vocoders.

VoicePay

Published:

  • Developed a voice-based payment platform that employs machine learning to facilitate payments through linguistics commands to focus on the booming digital payments market in India, catering to all user groups.
  • Reduced the amount of processing needed for the model while improving the response time by 20% and adaptability with 9 additional speech dialects.

Galaxy Classification based on Morphological Orientation

Published:

  • Proposed and implemented a transfer learning-based approach to classify galaxies based on its morphology using existing models such as VGG16, ResNet50, Xception, DenseNet, and InceptionNet.
  • Significantly improved classification accuracy by 17% compared to the previous architecture.

VAST 2022 Challenge - Identifying Demographics and Relationships

Published:

  • Developed an InfoVis system using React.js and D3.js to visualize demographic data, networking information, and financial statistics, enabling efficient city planning.
  • Employed Python for data preprocessing, utilizing pandas for grouping and Excel for database merging and outlier detection.
  • Enhanced React.js skills to manage large-scale datasets, implementing React state and Redux stores and addressing node clustering issues in D3 visualizations with anti-colliding forces.

teaching

Bachelor of Engineering, Information Technology

Pune Institute of Computer Technology, August 2016 - May 2020 , GPA 9.58/10

Coursework: Data Structures, Operating System, Machine Learning and Algorithm, Distributed Computing System, Computer Networks, Data Science and Big Data Analytics.

Master of Science, Computer Science

Arizona State University, August 2022 - May 2024 , GPA 4/4

Coursework : Data Mining, Data visualization, Knowledge Representation and Reasoning, Cloud Computing, Foundation of Algorithm, Software Requirements and Specifications.