I am a Senior Researcher at Sony Research India in Media Analysis Team. I did my masters from Indian Institute of Technology, Kanpur, under the supervision of Prof. Rajesh Hegde. During my masters I worked on Deep Learning based sound source localization in 3D, the details of which can be found here. I have also worked with Samsung RnD Bangalore, Fraunhofer IDMT(Germany) as an Early Stage Researcher in early 2022.
I have interned at Sony Research India(in 2020) and Gnani.ai(in 2021 also worked for full-time)
Updates:
- April 2024After a wonderful experience at Samsung RnD Bangalore, I have joined Sony Research India as a Senior Researcher where I will be working on speech recognition, multi-lingual Speaker Diarization and other similar topics.
- March 2024 Paper on Learning based MOS evaluation has been accepted in International Conference on Signal Processing and Communications (SPCOM)
- November 2023 Paper on Multi-lingual Speaker diarization got accepted in SPECOM.
- May 2023 Ranked 1st in the IWSLT2023 Challenge on Dialectal and Low-resource organised at ACL 2023.
- March 2023: Ranked 2nd in the DISPLACE Challenge organised at Interspeech 2023.