3

Pre-trained Audio Transformer as a Foundational AI Tool for Gravitational Waves
We introduce GW-Whisper, the first application of OpenAI’s state-of-the-art audio transformer model, Whisper, for gravitational wave data analysis. We fine-tune the pre-trained Whisper encoder for two critical applications – GW signal detection and glitch classification, demonstrating the robustness and versatility of the model. This work lays the foundation of adapting Whisper into a foundational AI model for gravitational wave data analysis.
Dr. Chayan Chatterjee, Abigail Petulante, Karan Jani, Jesse Spencer-Smith, Yang Hu, Roy Lau, Haowei Fu, Trang Hoang, Stephen Chong Zhao, Suyash Deshmukh
PDF Code Project DOI
Pre-trained Audio Transformer as a Foundational AI Tool for Gravitational Waves
Rapid Mass Parameter Estimation of Binary Black Hole Coalescences Using Deep Learning
Deep learning can be used to drastically decrease the processing time of parameter estimation for coalescing binaries of compact …
Alistair McLeod, Daniel Jacobs, Dr. Chayan Chatterjee, Linqing Wen, Fiona Panther
PDF DOI