Skip to content

R3plica

Harnessing The Power Of AI

AI, Deep Learning, Natural Language Process2 min read

shantanu acharya

Meet Shantanu Acharya

Artificial Intelligence Engineer @ Simbo.ai

Bangalore, India

Shantanu Acharya works as an Artificial Intelligence Engineer at Simbo.ai where he is currently building a state-of-the-art automatic speech recognition system in the medical domain.

Besides his job, he also works on various open-source projects from time to time.

Shantanu is passionate about NLP and Deep Learning and likes to work on challenging problems in this domain.


What inspired you to pursue a career in Artificial Intelligence?

I was marveled to find that people are making great strides using AI in domains like improving healthcare, fighting climate change, making self-driving cars e.t.c.

This motivated me to pursue a career in this domain so that I can also someday use my skills to make a meaningful impact on the world.

As I started my journey in AI, I specifically got inclined to the field of Deep Learning.

The core concept of Deep Learning that a program is able to identify patterns in huge amounts of data and improve itself on its own and achieve human-like performance still amazes me to this day.

Deep Learning has paved the way for modern AI and it is today used to improve almost every domain.

What is Natural Language Processing (NLP)?

Humans usually communicate with words, which are a form of unstructured data. This is unfortunate for computers and they are only able to work with structured data.

This is where Natural Language Processing (NLP) comes into play.

NLP is a field of AI whose goal is to make machines understand the language of humans with proper context and enables machines to perform a variety of tasks such as Machine Translation, Sentiment Analysis, Text Summarization e.t.c.

What is your main interest in working on Natural Language Processing (NLP)?

Understanding human languages is a formidable task for machines. Given the recent invention of Transformers in Deep Learning has helped NLP to make great strides in comprehending human languages but still, we are ways behind in making a true NLP system that can understand language like we humans do.

This means that there is still a lot left to explore and a lot of new techniques or algorithms left to be invented in order to make a perfect NLP system. This makes me excited to work in this field.

Where are you implementing Natural Language Processing (NLP)?

Currently, in the company I am working, we are using NLP to solve problems in the field of medicine.

We are implementing a bot that can fully understand conversations between a doctor and his/her patients and automatically generate an EMR. This can help save doctors a lot of time and allow them to focus more on their patients.

Specifically, my project in the company is to build a state-of-the-art Automatic Speech Recognition (ASR) system in the medical domain.

The system should be able to transcribe, with utmost accuracy, the conversations between a doctor and a patient without losing any medical context.

Do you have any AI project you are working on and want to share your experience with us?

Yes. Recently, I have been working on a project named "Flash".

It is an end-to-end Deep Learning platform that allows users to create, train, and deploy their own neural network models in a matter of minutes without writing a single line of code.

I had been learning about deploying AI models in resource-constrained environments as well as front-end development.

So this project was the perfect opportunity for me to implement various skills that I had learned and showcase them in one place.


For more about Shantanu Acharya AI projects go to github.com/shan18