About Me

Hello! I'm Karan Thakkar, a dedicated doctoral student in the Electrical and Computer Engineering Department at Johns Hopkins University, Baltimore, USA. My academic quest is deeply rooted in the fields of Artificial Intelligence (AI) and Brain-Inspired Computational Models for Audio. Working under the expert guidance of Professor Mounya Elhilali at the Laboratory of Computational Audio Perception, I am at the forefront of researching and developing groundbreaking auditory perception-inspired models.
For more information on my technical journey please see the attached CV.
In my free time, I indulge in painting and exploring the creative world of music mixing, allowing me to blend my technical expertise with artistic expression.
If you're interested in my research or have any questions, please feel free to reach out. I am always eager to engage in thoughtful conversations and collaborations.
Milestones in My Ph.D. Journey
- Oct'24: Article studying Neural Underpinings of Auditory Attention published in Nature Communications Biology.
- Aug'24: Completed my internship at Apple in Cupertino.
- Apr'24: DreamVoice: Text guided Voice Conversion accepted at the INTERSPEECH 2024 conference.
- Dec'23: Diffusion Based Target Sound Extraction and Self Supervised Audio Representation based Auditory Attention Decoding accepted at the ICASSP 2024 conference.
- Nov'23: Released a PyTorch implementation repo of Deep Learning based Auditory Envelope decoding from EEG.
- Jul'23: Attended the Telluride Neuromorphic Engineering Workshop.
- May'23: Participated in Workshop and Discussion at the CogHear Conference.
- May'23: Explicit Memory Multiresolution Adaptive (EMMA) Framework for Speech Enhancement and Separation published in EURASIP journal.