Customizable wake-up voice commands

A non-transitory computer-readable storage medium, including instructions, the instructions, when executed by one or more processors of an electronic device, cause the processors to perform operations comprising:

• receiving utterances from users and converting the utterances to commands from a vocabulary of predetermined commands, the vocabulary including a customization command to define a new wake-up utterance corresponding to a wake-up command;
• receiving a first utterance from a first user;
• in response to receiving the first utterance from the first user, and in accordance with a determination that the first utterance corresponds to the customization command to define a new wake-up utterance corresponding to the wake-up command, providing a first response to the first user;
• after providing the first response to the user, capturing a second utterance from the first user;
• and
• in response to receiving the second utterance from the first user:
• determining a likelihood of confusion for using the second utterance as the new wake-up utterance corresponding to the wake-up command, based at least in part on a frequency of use of the second utterance in a first selected corpus;
• in accordance with a determination that the likelihood of confusion for using the second utterance as the new wake-up utterance corresponding to the wake-up command is below a threshold, setting the second utterance as the new wake-up utterance corresponding to the wake-up command;
• and
• in accordance with a determination that the likelihood of confusion for using the second utterance as the new wake-up utterance corresponding to the wake-up command is above the threshold, generating an alert to the first user.

A method, comprising:

• receiving utterances from users and converting the utterances to commands from a vocabulary of predetermined commands, the vocabulary including a customization command to define a new wake-up utterance corresponding to a wake-up command;
• receiving a first utterance from a first user;
• in response to receiving the first utterance from the first user, and in accordance with a determination that the first utterance corresponds to the customization command to define a new wake-up utterance corresponding to the wake-up command, providing a first response to the first user;
• after providing the first response to the user, capturing a second utterance from the first user;
• and
• in response to receiving the second utterance from the first user:
• determining a likelihood of confusion for using the second utterance as the new wake-up utterance corresponding to the wake-up command, based at least in part on a frequency of use of the second utterance in a first selected corpus;
• in accordance with a determination that the likelihood of confusion for using the second utterance as the new wake-up utterance corresponding to the wake-up command is below a threshold, setting the second utterance as the new wake-up utterance corresponding to the wake-up command;
• and
• in accordance with a determination that the likelihood of confusion for using the second utterance as the new wake-up utterance corresponding to the wake-up command is above the threshold, generating an alert to the first user.