Securely executing voice actions using contextual signals to perform authentication

A system comprising:

• one or more computers and one or more storage devices storing instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising:
• receiving, from a first computing device, audio data representing a voice command spoken by a speaker;
• obtaining, based on the audio data representing the voice command, a speaker identification result indicating that the voice command was spoken by the speaker;
• determining, based on the speaker identification result indicating that the voice command was spoken by the speaker, a device identifier that corresponds to a second computing device of the speaker;
• selecting a voice action based at least on a transcription of the audio data;
• selecting a service provider corresponding to the selected voice action from among a plurality of different service providers that are configured to perform authentication using different types of contextual data;
• identifying, based on the selection of the service provider, one or more input data types, separate from speaker identification results based on voice input, that the selected service provider uses to perform authentication for the selected voice action;
• obtaining, using the device identifier that corresponds to the second computing device, contextual data from the second computing device that the selected service provider can use to authenticate the speaker without requiring the speaker to provide explicit authentic information, the contextual data comprising a status of the second computing device;
• obtaining, from the contextual data and without requiring the speaker to provide explicit authentication information, one or more values that correspond to the identified one or more input data types;
• and
• providing, to the selected service provider:
• a request to perform the selected voice action;
• the speaker identification result;
• and
• the one or more values that correspond to the identified one or more input data types.

One or more non-transitory computer-readable media storing instructions that, when executed by one or more computers, cause the one or more computers to perform operations comprising:

• receiving, from a first computing device, audio data representing a voice command spoken by a speaker;
• obtaining, based on the audio data representing the voice command, a speaker identification result indicating that the voice command was spoken by the speaker;
• determining, based on the speaker identification result indicating that the voice command was spoken by the speaker, a device identifier that corresponds to a second computing device of the speaker;
• selecting a voice action based at least on a transcription of the audio data;
• selecting a service provider corresponding to the selected voice action from among a plurality of different service providers that are configured to perform authentication using different types of contextual data;
• identifying, based on the selection of the service provider, one or more input data types, separate from speaker identification results based on voice input, that the selected service provider uses to perform authentication for the selected voice action;
• obtaining, using the device identifier that corresponds to the second computing device, contextual data from the second computing device that the selected service provider can use to authenticate the speaker without requiring the speaker to provide explicit authentic information, the contextual data comprising a status of the second computing device;
• obtaining, from the contextual data and without requiring the speaker to provide explicit authentication information, one or more values that correspond to the identified one or more input data types;
• and
• providing, to the selected service provider:
• a request to perform the selected voice action;
• the speaker identification result;
• and
• the one or more values that correspond to the identified one or more input data types.