Archiki Prasad
Research Scientist at Google DeepMind
Chapel Hill, North Carolina, United States
Summary
👤
Senior🎓
Top SchoolArchiki Prasad is a PhD student and applied ML researcher with eight years of experience bridging electrical engineering and machine learning, focused on time-series forecasting and end-to-end speech recognition. He has interned at top research labs (Adobe Research, AI2, Meta FAIR, Google DeepMind) and published work on accent effects in ASR at ACL and a cold-start forecasting method presented at WWW with an associated US patent filing. Comfortable moving between theory and engineering, he devised a novel Continuous Dynamic Key-Value Memory Network that considerably outperformed LSTM baselines for cold-start prediction. Based in Chapel Hill, he blends rigorous academic training from IIT Bombay with hands-on deployment experience and mentorship roles, making him adept at turning research insights into production-ready solutions.
8 years of coding experience
5 years of employment as a software developer
Indian Institute of Technology BombaySri Chaitanya Junior College, HydernagarDoctor of Philosophy - PhD Computer Science, Doctor of Philosophy - PhD Computer Science at The University of North Carolina at Chapel HillJubilee Hills Public School, Hyderabad
English, Hindi
Github Skills (35)
automatic-speech-recognition10
mutual-information10
paper10
robustness10
phones10
residual-networks9
pytorch9
python9
machine-learning9
speech-to-text9
tensorflow9
deep-learning9
source-separation9
audio8
deep-neural-networks8
Programming languages (4)
Github contributions (5)
archiki/Robust-E2E-ASR
Feb 2021 - Apr 2021
This repository contains the code for our upcoming paper An Investigation of End-to-End Models for Robust Speech Recognition at ICASSP 2021.
Contributions:46 commits, 41 pushes, 8 comments in 2 months
speech-recognitionautomatic-speech-recognitionrobustnessdeepspeech2end-to-end-learning
archiki/archiki.github.io
May 2020 - Nov 2022
Contributions:354 commits, 498 pushes, 3 branches in 2 years 6 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.