The company explains that it’s now built “better neural network acoustic models using Connectionist Temporal Classification and sequence discriminative training techniques” to upgrade its voice search functionality.
The new tech helps the voice search engine predict phonemes more quickly and differentiate between similar sounding letters.
In addition to improving voice search, Google says its aural wizardry also makes dictation on Android devices better, while requiring far less computing power.
➤ Google voice search: faster and more accurate [Google Research Blog]
Image credit: Shakuro