Hi, I'm
Indu
Currently, ML Engineer building intelligent systems at the intersection of machine learning and human impact — in education, healthcare, and accessibility.
MS in Electrical Engineering
Stanford University
- Depth: Signal Processing, Optimization and Machine Learning
- Breadth: Software and Hardware Systems
BE in Electronics and Communication
SSN College of Engineering
- Focus: Signal Processing and Machine Learning
Associate AI Engineer
Strategic Education Inc
Projects
Collaborated with CCRMA (Stanford University) and the Audiology department (Stanford School of Medicine) where I worked on using k-means clustering and data visualisation techniques to address the effects of non-auditory factors such as cognitive deficits or poor peripheral encoding from synaptopathy for speech recognition in quiet and noise.
Trained a Riff-P2P model on Slakh-2100 datasets using EC2 A10 GPUs to edit input audio by adding musical stems or instruments as directed by textual prompts, achieving good perceptual quality through subjective listening evaluations. Identified key limitations including melody leakage and inconsistent background preservation from source separation (using Spleeter), conducting analysis and documenting approaches for future mitigation.