Google has updated the technology behind its voice-powered Google Now tool to boost performance. The company said it "built better neural network acoustic models using Connectionist Temporal Classification and sequence discriminative training techniques" that are more accurate and better able to discern individual voices in noisy environments. The updated tools require less computational power are also much faster. Google said it has made this technology available to the Google Search app for Android and iOS. Voice-based search and voice commands should demonstrate marked improvement.
More...
Bookmarks