This week in AI & Machine Learning: A cautionary QC tale from The Simpsons, a new approach to text-to-speech from Google, a game-changing ML model for baseball and more.
Yesterday was National Beer Day and, as a lifelong fan of The Simpsons, I found myself thinking of Homer Simpson and Barney Gumble. I’m reminded of their trip to the Duff Beer factory every time I visit Plainsight’s website and see this demonstration on our home page:
In the classic Season 4 episode “Duffless,” Homer and Barney visit the factory to learn how their beloved beer is made. They get a preview of upcoming flavors, taste varieties of Duff from all around the world, and meet Phil, “the most important man on the tour.” With amazing accuracy, Phil manages quality control by identifying contaminated products and removing them from the assembly line.
Artificial Intelligence News
A New Approach to Text to Speech
Dialogue replacement and dubbing are traditionally challenging. It can take several thorough edits to effectively sync newly recorded audio with existing video. A team of Google engineers offer a proof concept for a new kind of visually-driven text-to-speech AI model, VDTTS.
Standard speech recognition models focus on the speaker’s mouth. This new approach would leverage footage of the speaker’s full face to avoid inadvertently excluding important information. The model can make observations related to factors like emotion and timing that a more traditional text-to-speech model might miss. Read the full proof of concept summary and learn more about using Plainsight on the Google Cloud Marketplace.
Measuring Baseball Performance with ML
Researchers at Penn State University believe their new approach to measuring performance on the baseball diamond is better than traditional approaches using statistical analysis. Leveraging the latest in computer vision and natural language processing, their machine learning model works to understand the context around each play. They believe their work lays the groundwork for fundamental changes to the still-growing world of sabermetrics. Check out how computer vision enhances the in-stadium experience for spectators.
EU Approves AI for Autonomous X-Ray Scanning
A new tool called ChestLink, which is capable of autonomously analyzing chest X-rays, has earned regulatory approval for use in the European Union. ChestLink eliminates unnecessary review time by automatically sending patient reports in response to abnormality-free scans. Only x-rays with potential red flags are reserved for review by a radiologist. Vision AI’s use in medical imaging remains controversial, but there are plenty of less contentious use cases for the industry. Learn how computer vision is empowering healthcare providers to offer a higher quality of care.
Join our Community
See you next week! Until then, keep the conversation going on Plainsight’s AI for All Slack Channel.
About the Author & Plainsight
Bennett Glace is a B2B technology content writer and cinephile from Philadelphia. He helps Plainsight in its mission to make vision AI accessible to entire enterprise teams–the ML power users, as well as the subject matter experts and non-technical users.
Plainsight’s vision AI platform streamlines and optimizes the full computer vision lifecycle. From data annotation through deployment, customers can quickly create and successfully operationalize their own vision AI applications to solve highly diverse business challenges.