Somshubra Majumdar

Somshubra Majumdar is a senior research scientist working on the NVIDIA NeMo toolkit. He received a bachelor's degree in Computer Engineering from the University of Mumbai in 2016, and a master's degree in Computer Science from the University of Illinois at Chicago in 2018. His research interests include automatic speech recognition, speech classification, time series classification, and practical applications of deep learning.
Somshubra Majumdar

Posts by Somshubra Majumdar

Generative AI

Turbocharge ASR Accuracy and Speed with NVIDIA NeMo Parakeet-TDT

NVIDIA NeMo, an end-to-end platform for developing multimodal generative AI models at scale anywhere—on any cloud and on-premises—recently released... 6 MIN READ
Image of two people sitting in their cubicles with speech recognition visualizations in the background.
Conversational AI

Pushing the Boundaries of Speech Recognition with NVIDIA NeMo Parakeet ASR Models

NVIDIA NeMo, an end-to-end platform for the development of multimodal generative AI models at scale anywhere—on any cloud and on-premises—released the... 6 MIN READ
Conversational AI

NVIDIA Speech and Translation AI Models Set Records for Speed and Accuracy

Speech and translation AI models developed at NVIDIA are pushing the boundaries of performance and innovation. The NVIDIA Parakeet automatic speech recognition... 8 MIN READ
Conversational AI

Controlled Adaptation of Speech Recognition Models to New Domains

Have you ever tried to fine-tune a speech recognition system on your accent only to find that, while it recognizes your voice well, it fails to detect words... 8 MIN READ
Conversational AI

Improving Japanese Language ASR by Combining Convolutions with Attention Mechanisms

Automatic speech recognition (ASR) research generally focuses on high-resource languages such as English, which is supported by hundreds of thousands of hours... 5 MIN READ