Google patents speech system that learns from your app usage
This filing describes a method where a device uses a 'biased' speech transcription, meaning it guesses what you said based on phrases you often use. It then checks if you actually used the app or feature you asked for, using that success or failure to adjust how accurately the speech recognizer works in the future.
In the filing’s own words
A method includes receiving a biased transcription for a voice command spoken by a user and captured by a user device, the biased transcription biased to include a biasing phrase from a set of biasing phrases specific to the user. The method also includes instructing an application executing on the user device to perform an action specified by the biased transcription for the voice command, and receiving one or more user behavior signals responsive to the application performing the action specified by the biased transcription. The method further includes generating, as output from a confidence model, a confidence score of the biased transcription based on the one or more user behavior signals input to the confidence model and, based on the confidence score output from the confidence model, training a speech recognizer on the biased transcription.
What exactly they claim (claim 1)
1. A computer-implemented method executing on data processing hardware that causes the data processing hardware to perform operations comprising: receiving a biased transcription for a voice command, the biased transcription biased to include a biasing phrase from a set of biasing phrases specific to the user; instructing an application to perform an action specified by the biased transcription for the voice command; in response to the application performing the action specified by the biased transcription for the voice command, receiving a behavior signal representing an interaction between the user and the application associated with the application performing the action specified by the biased transcription; processing, by a trained machine learning model, the behavior signal representing the interaction between the user and the application to generate a confidence score associated with the biased transcription for the voice command; and training a language model based on the confidence score associated with the biased transcription.
Facts
- Company
- Google (Google LLC)
- Official title
- Training Speech Recognizers Based On Biased Transcriptions
- Publication number
- US20260279342A1
- Application number
- 19679735
- Filed
- May 17, 2026
- Published
- Sep 17, 2026
- Inventors
- 2
- Claims
- 20
Classified under
G10L 15/063 Physics & computingG10L 15/08 Physics & computingG10L 15/22 Physics & computingG10L 2015/0636 Physics & computingG10L 2015/088 Physics & computingG10L 2015/223 Physics & computingMore from Google in AI & software
- Google patents video search that answers questions using AI descriptions Sep 15, 2026
- Google patents photo tool that removes people and their gear Sep 15, 2026
- Google patents AI that writes live meeting notes and summaries Sep 15, 2026
- Google patents AI tool that turns messy emergency notes into clear messages Sep 3, 2026
- Google patents AI that clicks through apps to finish tasks for you Sep 24, 2026
Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.