Constantin Orasan's page

All kind of random stuff on NLP, AI, photography and who knows

 

The recent developments in Artificial Intelligence (AI) have led to a variety of technologies that have the potential to support interpreters in their everyday activities. The most notable such technology is Automatic Speech Recognition (ASR), which takes speech and transcribes it to its written form. In scenarios where ASR is used by interpreters within Computer Assisting Tools, it can display terms that are used by the speaker together with their translation, show only the numbers mentioned and even list the full transcription of the speech in real-time.

The EmpASR project is an AHRC funded project that aims to maximise the impact of our recently completed InnovateUK funded research, Harnessing court data using NLP and spoken language technology, by embedding its research outcomes in the development of bespoke ASR services for interpreters and providing training in using ASR. The focus will be on supporting interpreters, language service providers and other users of ASR services to benefit from the latest developments in artificial intelligence (AI).

One of the deliverables of the project is the development of a training course focusing on ASR literacy for interpreters. It will educate them on how AI and ASR work, how interpreters can benefit from this technology and when it is appropriate to use it. The course will also include a practical part where participants will learn how to customise an ASR engine.

Team

  • Constantin Orasan, Lead
  • Sabine Braun, Co-lead
  • Andreea Deleanu, research assistant
  • Shiyi Tan, research assistant
  • Diana Singureanu, advisor

Outputs



This page was last modified on 26th March 2025.

More about my research