Task initiation using long voice commands

摘要

In various implementations, upon receiving a given voice command from a user, a voice-based trigger may be selected from a library of voice-based triggers that has been previously used across a population of users. The library may include mapping (s) between each speech-based trigger and response action (s) that were executed earlier in response to the speech-based trigger. The selecting may be based on a measure of similarity between the given voice command and the selected voice-based trigger. One or more response actions associated with the selected speech-based trigger in the library may be determined. Based on the one or more response actions, a current response action (s) may be performed by the client device. A response associated with executing the current response action (s) may be received by the user and used to change a strength of an association between the selected voice-based trigger and the one or more response actions.