AI Tool Transforms UK Supreme Court Hearings Into Searchable Transcripts

The Study

In a new study, published in the journal Applied Sciences, researchers detail how they developed an artificial intelligence (AI) system that can automatically transcribe UK Supreme Court hearings and link them directly to the written judgments, enabling lawyers, academics, and the public to navigate justice like never before.

Every year, more than 449,000 cases are heard in UK tribunals, yet recordings of court hearings remain difficult to access. Traditional transcription is slow, costly, and prone to errors. Off-the-shelf speech recognition tools struggle with courtroom language, mishearing phrases like "my lady" (pronounced "mee-lady" by barristers when addressing a female judge) as "melody" or legal terms like "inherent vice" as "in your advice.

Custom Courtroom AI

To tackle this, researchers developed a custom speech recognition system trained on 139 hours of Supreme Court hearings and legal documents. By fine-tuning the model with specialist vocabulary and court etiquette, the system reduced transcription errors by up to 9% compared with leading commercial tools. It also proved more reliable at capturing crucial entities such as provisions, case names, and judicial titles.

Professor Constantin Orăsan, co-author of the study and Professor of Language and Translation Technologies at the University of Surrey, said:

"Our courts deal with some of the most important questions in society. Yet the way we record and access those hearings is stuck in the past. By tailoring AI to the unique language of British courtrooms, we've built a tool that makes justice more transparent and accessible, whether you're a barrister preparing an appeal or a member of the public trying to understand why a judgement was reached."

User interface for linking judgement to bookmarks in video court sessions

Semantic Linking

The second part of the project used AI to semantically match paragraphs of judgments with the precise timestamp in the video where the argument was made. A prototype interface now allows users to scroll through a judgment, click on a paragraph, and instantly view the relevant exchange from the hearing. Tests showed that the system correctly linked text and video, achieving an F1 score of 0.85.

Understanding the F1 Score

An F1 score is a way of measuring how well a system balances two things:

• Precision, of all the results it gave, how many were actually correct?
• Recall, of all the correct results that existed, how many did it manage to find?

It penalizes a system that excels in one area but struggles in the other. It ranges from 0 to 1:

• 1.0 means perfect precision and recall; the system found everything and made no mistakes.
• 0 means total failure.

Impact and Adoption

Evaluation with real users showed that their productivity is dramatically increased when using the interface. Without AI assistance, a legal expert needed 15 hours to identify 10 links; however, with AI support, they were able to validate 220 links in just 3 hours.

The tool is already attracting interest from legal bodies, including the UK Supreme Court and the National Archives. By reducing hours of manual searching to seconds, it promises to help lawyers prepare cases, speed up legal training, and enable the public to see how decisions are made.