Voice-controlled virtual assistants typically maintain a standard output volume level. In certain circumstances, this leads to a response from the virtual assistant that is either too loud or too low. For example, if the last-used context of the virtual assistant was a party with high ambient noise, then the virtual assistant continues responding too loudly even after the party has ended and the ambient noise level has dropped.

This disclosure describes techniques to automatically adapt the output volume level of a virtual assistant based on current context, user preferences, user feedback, etc. A machine learning model predicts an optimum volume level for the virtual assistant, sets the volume level, and adapts it based on user feedback. With permission, user feedback serves as training data for predicting volume level in different contexts.

Creative Commons License

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.