My name is Sakshi. I am currently a 1st year C.S. Ph.D. student at the University of Maryland, College Park, advised by Prof. Ramani Duraiswami at PIRL Lab and Prof. Dinesh Manocha at Gamma Lab on audio and language processing. Currently I am working on improving complex reasoning tasks in audio and natural language models. I completed my M.S. from UMass Amherst in 2022 where I worked with Prof. Ethan Zuckerman on Extreme Speech detection on YouTube. Previous to UMass, I served as a Software Engineer II at Cisco Systems, Bangalore. My primary work at Cisco involved building network assurance software systems for Cisco’s Service Provider customers. My current research focuses on deep learning for audio processing, with a focus on building efficient models and the integration of language as a tool to improve the performance of audio processing tasks.
CV / Resume: link
Email ID: ssakshi@umd.edu
Updates
| Sept 2024: | We released MMAU, the most comprehesive audio understanding and reasoning benchmark yet! Check it out here ! |
| Sept 2024: | EH-MAM and GAMA are accepted to EMNLP 2024! |
| Aug 2024: | Joined C.S. Ph.D. program at UMD!. |
| June 2024: | We release GAMA, an LLM with strong audio-understanding capabilities! Details under the Research section. |
| Jan 2024: | 1 paper accepted to ICLR 2024! |
| March 2024: | 2 papers accepted to NAACL 2024! |
| May 2024: | 2 papers accepted to ACL 2024! |
| Dec 2023: | Attended EMNLP 2023 in-person in Singapore! |
| Oct 2023: | 1 paper accepted to EMNLP 2023! Details under the research section. |
| Aug 2022: | Joined M.S. C.S. program at UMass Amherst!. |
| July 2022: | 1 paper accepted to InterSpeech 2022! |