I am currently a Ph.D. candidate at Carnegie Mellon University in the Department of Electrical and Computer Engineering. I am currently a member of the Center for Voice Intelligence and Security (CVIS) and Machine Learning for Signal Processing (MLSP) group, currently advised by Prof. Bhiksha Raj. I have also been a member of the Sinbad group at CMU, advised by Prof. Florian Metze

I graduated with a Masters in Electrical and Computer Engineering from Carnegie Mellon University in August 2020, and a B.Tech in Electronics and Communication Engineering from Amrita University in Bangalore, India in 2018.

I love to listen to music and practice vocals outside of my work :)

Updates

• 2023-01-15: Thrilled to share that our work on [AugSumm: ]

• 2023-07-26: We will organize a special session at ICASSP 2024 on Efficient Modeling of Long Sequences with Applications to Speech and Audio. Please consider submitting your work!

• 2023-06-12: Our work on SLUE Phase-2: A Benchmark Suite of Diverse Spoken Language Understanding Tasks was accepted for publication at ACL 2023. We are releasing code and new datasets for 4 tasks including spoken question answering, speech summarization, named entity localization and dialog act classification in collaboration with ASAPP, NTU Taiwan and TTI-Chicago.

• 2023-06-08: I had the opportunity to discuss a portion of my thesis work at the Rising Stars Session at ICASSP 2023 in Greece.

• 2023-05-17: Our work on BASS: Blockwise Adaptation for Speech Summarization was accepted for publication at Interspeech 2023.

• 2022-03-21: I will be returning as an intern to Meta in Seattle and have the privilege of working with Ozlem Kalinli, Suyoun Kim and Mike Seltzer.

• 2023-02-16: Our work on Speech summarization of long spoken document: Improving memory efficiency of speech/text encoders led by NTT,Japan was accepted for publication at ICASSP 2023.

• 2023-02-16: Our work on Egocentric Audio-Visual Noise Suppression, completed at Meta during Summer 2022 was accepted for publication at ICASSP 2023.

• 2023-01-15: We are organizing the Low-resource Spoken Language Understanding Evaluation Challenge Special Session at Interspeech 2023. Please consider submitting.

• 2022-12-16: I successfully presented my Thesis Proposal at Carnegie Mellon University. Thanks to my Committee Dr. Bhiksha Raj,Dr. Shinji Watanabe, Dr. Florian Metze and Dr. Rita Singh

• 2022-11-01: I will attend the Neural Information Processing Systems (NeurIPS) 2022 conference in Vancouver, Canada.

• 2022-10-29: Our work on Cross-Utterance Context for Multimodal Video Transcription was presented at ASILOMAR 2023, held at Pacific Grove,CA,USA

• 2022-05-21: Our work on End to End Speech Summarization with Restricted Self-Attention was presented at ICASSP 2022 in Singapore.

• 2022-06-13: Our work on Self-supervision and Learnable STRFs for Age, Emotion, and Country Prediction was awarded 2nd Place and was accepted for publication at the ICML 2022 Workshop on Expressive Vocalizations Workshop and Competition

• 2022-03-21: I will be an intern at Meta in Seattle with AI Speech Org under Dr. Mike Seltzer

• 2022-02-16: Our work on End to End Speech Summarization with Restricted Self-Attention was accepted for presentation at ICASSP 2022.

• 2022-02-20: I joined the Machine Learning for Signal Processing group at Carnegie Mellon University as a Ph.D. student, advised by Bhiksha Raj.