We submitted a paper on speaker representation learning -- This work learns persistent speaker representations directly from overlapping speech mixtures, enabling speakers to be re-identified across long-form conversations without enrollment audio, diarization supervision, or explicit tracking training.
I am happy to share that I have accepted to intern at Bose Corporation as Audio Machine Learning Researcher. Looking forward to work on some interesting projects in Audio AI
I am happy to share that I have begun my PhD in the Computer Science and Engineering department at the University of Michigan, Ann Arbor
If you are at Rotterdam from August 17-21, 2025, and want to have a chat on speech technologies, feel free to hit me up!
Signed an offer to Intern at Skyworks AIS team in Summer'2025 -- Headstart towards my PhD
I'll be travelling to Philadelphia to present my masters research project at AAAI 2025
Our work on audio denoising using SSMs at BrainChip was recently submitted to Interspeech 2025.
Excited to share that I will be joining University of Michigan, CSE for my PhD in Fall 2025
My master's main research project was accepted at AAAI 2025 Workshop on Health Intelligence
