Ankita Pasad

Research Scientist at NVIDIA

California, United States
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts

Summary

🤩
Rockstar
🎓
Top School
Ankita Pasad is a research scientist at NVIDIA with nine years of experience at the intersection of speech representation, semi-supervised learning, and multimodal spoken language understanding. Her work focuses on interpretability of pre-trained speech models and leveraging unlabeled data through semi-supervised and consistency-driven objectives, a thread that connects internships at Google (video-based spatio-temporal consistency for segmentation) and ASAPP (SLUE benchmark). She holds a PhD from Toyota Technological Institute at Chicago and dual B.Tech/M.Tech degrees from IIT Bombay in communications and signal processing, bringing strong theoretical grounding to applied problems. Based in California, she blends academic rigor with industry impact, often translating evaluation insights into benchmarks and practical model analysis. An underappreciated strength is her cross-domain fluency—applying ideas from vision and video consistency to advance robustness and interpretability in speech systems.
code9 years of coding experience
bookDoctor of Philosophy Computer Science, Doctor of Philosophy Computer Science at Toyota Technological Institute at Chicago
bookIndian Institute of Technology Bombay
bookVidya Niketan
stackoverflow-logo

Stackoverflow

Stats
1reputation
0reached
0answers
0questions
github-logo-circle

Github Skills (49)

speaker-diarization10
speech-to-text10
pytorch10
machine-translation10
speech-processing10
chainer10
speech-enhancement10
text-to-speech10
speech-synthesis10
voice-conversion10
multimodal10
text-normalization10
large-language-models10
nmt10
kaldi10

Programming languages (1)

Python

Github contributions (5)

github-logo-circle
Contributions:32 pushes, 2 branches in 6 years 9 months
ankitapasad/NeMo

Nov 2024 - Apr 2025

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)
Contributions:48 pushes, 9 branches in 4 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.
Request Free Trial
Ankita Pasad - Research Scientist at NVIDIA