Experience

 
 
 
 
 
October 2022 – Present
Redmond, WA, USA

Sr Applied Scientist

Microsoft

E2E Speech modeling team, AI Cognitive Services group.
 
 
 
 
 
September 2021 – September 2022
Cambridge, MA, USA

Research Scientist

Mitsubishi Electric Research Laboratories

Member of Speech & Audio Group.
 
 
 
 
 
May 2020 – August 2020
Bellevue, WA, USA

NLP Research Intern

Tencent AI Lab

Worked with Dr. Chao Weng and Dr. Dong Yu on multi-source localization and its importance for multi-talker speech recognition.
 
 
 
 
 
May 2019 – August 2019
Bellevue, WA, USA

NLP Research Intern

Tencent AI Lab

Worked with Dr. Chao Weng and Dr. Dong Yu on target speech extraction with end-to-end speech recognition objectives.
 
 
 
 
 
May 2018 – August 2018
Kyoto, Japan

Research Intern

NTT Communication Sciences Lab

Worked with Dr. Marc Delcroix on speaker and environment adaptation for end-to-end noise robust speech recognition.
 
 
 
 
 
September 2017 – August 2021
Baltimore, MD, USA

Research Assistant

Center for Language & Speech Processing, Johns Hopkins University

Working with Dr. Shinji Watanabe on robust speech recognition, end-to-end speech recognition, multi-source localization, far-field speech enhancement and separation.
 
 
 
 
 
July 2015 – August 2016
Bangalore, India

Network Software Engineer

Intel

Worked in the Axxia network accelerator team, Data Center Group. Contributed to IPv6 module and automation of performance benchmarks.
 
 
 
 
 
July 2012 – July 2015
Chennai, India

Project Associate

IIT Madras

Worked in a consortium project sponsored by DeitY, Govt. of India under the supervision of Prof. Hema Murthy. I was involved in the development of a common framework for HMM based speech synthesis of 13 Indian languages. I developed an automatic segmentation tool and also worked on using syllable as the fundamental unit of synthesis

Selected Publications

Recent Publications

More Publications

An Exploration of Self-Supervised Pretrained Representations for End-to-End Speech Recognition

Preprint

The 2020 ESPnet Update: New Features, Broadened Applications, Performance Improvements, and Future Plans

Preprint

ESPnet-SE: End-to-End Speech Enhancement and Separation Toolkit Designed for ASR Integration

Preprint

Contact