Nithin Rao Koluguri
/
Senior Research Scientist at NVIDIA Conversational AI
Nithin is a Senior Research Scientist at NVIDIA Conversational AI, where he leads cutting-edge work in speech recognition, speaker verification, diarization, and large-scale speech-language models. He has played a pivotal role in the development of several high-impact technologies, including the TitaNet architecture for speaker recognition, which has become a widely adopted model with over 1.5 million downloads per month on Hugging Face. He also co-developed the first speaker diarization modules in NeMo and helped scale FastConformer ASR models to the billion-parameter range. Most recently, Nithin has been leading the development of the Parakeet model series, with Parakeet-tdt-0.6b-v2 holding the #1 position on the Hugging Face Open-ASR leaderboard.
Before joining NVIDIA in 2020, Nithin earned his Master’s degree in Electrical and Computer Engineering from the University of Southern California, where he conducted research at the Signal Analysis and Interpretation Laboratory (SAIL) under Professors Shrikanth Narayanan and Panayiotis Georgiou. His background also includes work at Bose, Robert Bosch, and the SPIRE Lab at the Indian Institute of Science, where he contributed to projects ranging from NLP and computer vision to using speech biomarkers for neurodegenerative disease detection. His research interests span speech signal processing, machine learning, and the development of intelligent audio systems that advance human-computer interaction.