The Machine Translation (MT) workstream aims to create the largest and most diverse Thai-to-English (TH-EN) dataset as well as baseline models for translation tasks of the language pair.

Our objective is to develop machine learning models for recognizing emotions using the subtle nuances in the speech utterance such as tone, pitch, etc. Emotion perception devices would be useful in many industries including healthcare, entertainment and marketing.

Automatic Speech Recognition (ASR) technology is the technology that turns speech into text. It has become prevalent in our lives with the usage of smartphones.

OCR or Optical Characters Recognition is the process of transforming an image of text or characters into digital form.