How Warner Bros. Discovery uses audio analysis to improve data accuracy and enrich the fan experience
Media Blog
This article discusses how Warner Bros. Discovery (WBD) used AWS serverless components to improve the accuracy of data streams that power fan experiences for their streaming platform by analyzing audio from sports events.
Specifically, the article covers:
- The challenges of latency and accuracy in aligning video and data feeds for timeline markers
- Using audio analysis and mel spectrograms to detect events like referee whistles and crowd cheering
- Detecting kickoff by identifying the referee's whistle and validating with Amazon Rekognition
- Aligning data markers to crowd excitement peaks detected in the audio
- The serverless AWS architecture used for processing, including S3, Lambda, DynamoDB, and CloudWatch
- Results showing high accuracy in detecting events compared to human observation
- Conclusion on how audio analysis enabled a cost-effective, real-time solution
The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.
Related articles
Oct 15
2025
2025
Warner Bros. Discovery Sports engages fans using scaled audio data analysis on AWS
May 7
2024
2024
Warner Bros. Discovery Sports implements further live cloud-based production using AWS
Nov 25
2025
2025
Warner Bros. Discovery achieves 60% cost savings and faster ML inference with AWS Graviton
May 5
2025
2025
Amazon Bedrock Data Automation now supports extraction of custom insights from audio
The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.