Home
As a Senior Data Scientist at NVIDIA, I help cloud customers train and deploy conversational AI models at scale, using NVIDIA’s GPUs and software. I have a passion for speech and audio data, and I specialize in text-to-speech (TTS) algorithms and applications. I have contributed to multiple TTS projects, such as scaling NVIDIA’s Multi-speaker Multi-lingual TTS systems with Zero-shot TTS to Indic Languages.
I have a Master of Science in Computer Science from the University of Colorado Boulder, where I explored and published papers on various topics, such as cognitive science, climate prediction and AI for education. My academic background and professional experience have taught me how to apply deep learning to solve real-world problems and deliver impactful solutions. I am always eager to learn new skills and technologies, and to collaborate with other experts and innovators in the field of conversational AI.
If you are interested in collaborating, feel free to drop a note. If you are looking connect 1-1 with me, book time on my calendar.
Research
Scaling NVIDIA’s Multi-speaker Multi-lingual TTS Systems with Zero-Shot TTS to Indic LanguagesAkshit Arora, Rohan Badlani, Sungwon Kim, Rafael Valle, Bryan Catanzaro | |
VANI: Very-lightweight Accent-controllable TTS for Native and Non-native speakers with Identity PreservationRohan Badlani, Akshit Arora, Subhankar Ghosh, Rafael Valle, Kevin J. Shih, João Felipe Santos, Boris Ginsburg, Bryan Catanzaro project page, pdf, code, blog, talk | |
Does Deep Knowledge Tracing Model Interactions among Skills?Shirly Montero, Akshit Arora, Sean Kelly, Brent Milne, Michael Mozer | |
Interactive landslide simulator: a tool for landslide risk assessment and communicationPratik Chaturvedi, Akshit Arora, Varun Dutt |
Recent News
- [July 2024] Published AWS Machine Learning Blog: Accelerate your generative AI distributed training workloads with the NVIDIA NeMo Framework on Amazon EKS. #engineering
- [May 2024] Published AWS HPC Blog: Large scale training with NeMo Megatron on AWS ParallelCluster using P5 instances. #engineering
- [April 2024] Sungwon Kim and I presented our work towards LIMMITS 2024 at IEEE ICASSP 2024 in Seoul, South Korea on April 17, 2024. [pdf, pptx] #research
- [March 2024] Published NVIDIA Tech Blog: NVIDIA Speech and Translation AI Models Set Records for Speed and Accuracy #research
- [March 2024] Rohan Badlani and I gave a talk at NVIDIA GTC 2024 on Speaking in Every Language: A Quick-Start Guide to TTS Models for Accented, Multilingual Communication - S62517 on March 18. #research
- I also volunteered as a Teaching Assistant at one of the tutorials on AI Safety Defenders: Reinforcing Medical Boundaries with Guardrails - DLIT61528. #mentoring
- Checkout my top 5 expert insights here from GTC here.
More updates here.