Context configurable keywords

A computing system, comprising:

• at least one processor;
• and
• at least one memory comprising instructions that, when executed by the at least one processor, cause the computing system to:
• determine first configuration data associating a first model with a first function and a first contextual state, the first model being usable by a first device to determine that speech detected by the first device includes at least one first word;
• send the first configuration data to the first device to configure the first device to cause the first function to be executed in response to the first model determining, while first device is in the first contextual state, that the at least one first word has been spoken;
• determine second configuration data associating the first model with a second function different from the first function and a second contextual state different from the first contextual state;
• and
• send the second configuration data to the first device to configure the first device to cause the second function to be executed in response to the first model determining, while the first device is in the second contextual state, that the at least one first word has been spoken.