In this project, we are working towards predicting speaker’s attribute from audio.
In this project, we are working towards model for automatically translating medical reports in low-resource languages.
We work on direct speech-to-speech translation systems that convert spoken audio in one language directly into spoken audio in another.
This project focuses on building robust speech-to-text translation and transcription systems, including benchmark datasets and models for low-resource languages.
We design lightweight and efficient models for time-series forecasting and analysis across diffrent domains.
Our research focuses on developing accurate and efficient machine translation systems for low-resource.
This project explores decoding readable text directly from EEG brain signals, using transformer-based architectures to bridge neural activity and language.
We study text-to-text tasks such as summarization, sentiment analysis, and information extraction across languages and domains.
