Google Using AI to Explore the Future of News Audio
https://blog.googleGoogle is using a machine learning ↔ human ↔ machine learning feedback loop to correct common machine learning errors in auto transcripts. They are beginning to test out a feedback loop in which newsrooms could identify common transcription errors to improve the machine learning model.
They are hoping improvements into these speech-to-text models will help convert audio to text faster, ultimately helping people find audio news more effectively.
When they get this to an acceptable standard .. imagine getting all the podcast content indexable for searches?
