I am a research scientist at Meta, Reality Labs Research. Between 2016-2022, I did audio and ML research at Audio Analytic, Telecom Paris and Technicolor. My doctoral thesis involved learning representations for robust audio-visual scene analysis.

I am also passionate about music - grew up learning indian classical, record scarcely but have a song on my mind at all times.

Recent updates

• Apr’25: Attended ICASSP 2025!
• Feb’25: Multimodal audio highlighting accepted at CVPR 2025!
• Feb’25: Invited talk at IIT Jodhpur
• Jun’24: Third edition of MMM course
• Apr’24: Invited talk at University of Rochester (Voices of XR)
• Dec’23: Audio interpretability extended work accepted at IEEE TASLP!
• Sep’23: Attended DCASE 2023, see our spotlight talk here
• Jun’23: Second edition of our MMM course
• Sep’22: Audio interpretability work with Jayneel Parekh accepted at NeurIPS 2022!
• May’22: New course on Music, Math and Machines (MMM) with Prof. Pratik Shah, IIIT Vadodara