Speakers:
Machine Learning in Media & Entertainment: Captions on Max streaming service
Date:
Tuesday, June 3, 2025
Time:
11:20 am
Summary:
The media and entertainment world are increasingly looking to AI to cut some of the cost-intensive processes involved in making and producing content. Warner Bros. Discovery is a leading global media and entertainment company, renowned for producing content such as Harry Potter, Game of Thrones, Big Bang Theory and Friends.
In this case study, Sravanthi will share how Warner Bros. Discovery is improving the cost efficiency of the caption generation process for its Max Streaming Service using an internally built product, “Caption AI.” Caption AI cuts costs relating to generating captions by up to 50%, while creating new file captions also takes up to 80% less time. Caption AI combines custom models for Speech to Text, Speaker Segmentation, and On-Screen placement of Caption Blocks. Caption AI outputs are edited and reviewed by manual caption transcribers to ensure accuracy and context, maintaining high quality in the final captions.
Speakers:
How AI-Driven Error Classification Enhances Machine Translation Evaluation
Date:
Tuesday, June 3, 2025
Time:
11:45 am
Summary:
Incorporating AI into translation workflows requires an automated, nuanced approach to evaluating machine translation (MT) quality. Traditional AI methods offer a single quality score, lacking the depth of human Linguistic Quality Assessment (LQA), which provides detailed error categorization and criticality.
This session introduces an AI-powered tool designed to replicate human LQA, classifying error types and severity. With ~94% accuracy and ~56% recall, this model outperforms traditional methods. Attendees will learn how our ML engineers built and tested this tool using leading large language models (LLMs) across five languages and thousands of segments and explore its real-world impact on translation workflows.