Google Assistant is using on-device “Personalized speech recognition” on the Pixel 7 and 7 Pro to get “better at recognizing your unique speaking style, words, and phrases.”

This might include the names of people and places that are less common or more unique to you. Google’s Personalized speech recognition works by “saving and learning from your Assistant interactions, including audio, securely on your device.” Typed queries and other recognized text is also used.

For example, you might correct an acronym when you ask Google Assistant something, or select a suggested alternative for the name of a place when using the Assistant to navigate.

Google encourages users to correct Assistant by “selecting a suggestion chip, directly editing the text in an Assistant interaction, or repeating your question back-to-back.”

Google Assistant can use your past corrections to learn from its mistakes and improve over time.

This feature was enabled during the Google Assistant set-up process on the Pixel 7 or 7 Pro. It can be turned off by going to Assistant settings on your Pixel 7 > You > Your speech recognition > Personalized speech recognition off/on.

Disabling will delete “any Assistant interactions that were used to train the model” from your phone. Turning off will not impact how data is collected, stored, or used for Assistant Voice Typing on Gboard, Voice and Audio Activity, Voice Match, Personal Results, Improve Assistant through Federated Learning, Improve Gboard through Federated Learning, or Web & App Activity.

More on Pixel 7:

FTC: We use income earning auto affiliate links. More.

Check out 9to5Google on YouTube for more news:

You’re reading 9to5Google — experts who break news about Google and its surrounding ecosystem, day after day. Be sure to check out our homepage for all the latest news, and follow 9to5Google on Twitter, Facebook, and LinkedIn to stay in the loop. Don’t know where to start? Check out our exclusive stories, reviews, how-tos, and subscribe to our YouTube channel

About the Author

Abner Li

Editor-in-chief. Interested in the minutiae of Google and Alphabet. Tips/talk: