Meta AI Develops ‘Utterance Clustering’ Dataset for Improved Automatic Speech Recognition

  • Meta AI has developed a new dataset using an ‘utterance clustering’ method to improve the performance of automatic speech recognition (ASR) systems.
  • The dataset includes over 27,000 command utterances from a diverse group of speakers, focused on seven main themes.
  • Initial results showed a 10% overall increase in ASR performance, with significant improvements in recognizing accents and understanding the 66-85 age demographic.
Join 2 million subscribers

A curated newsletter that summarizes the important news at the intersection of Global tech, India Tech and AI.

Delivered 8 AM. Daily.
nextbigwhat We would like to show you notifications for the latest news and updates.
Allow Notifications