How Voice Assistants Listen for More Commands Without a Wake Word

This patent describes how a voice assistant can keep listening for follow-up commands after an initial request, without needing you to say its wake word again, based on the type of command you just gave.

What it covers

The patent details a method for a voice assistant system to maintain an "attention span" after a user's initial command. After a device receives a first command, triggered by a keyword, and a server processes it and sends a response (Claim 1), the server decides if that command type (e.g., asking a question) is likely to be followed by another command. If so, the server instructs the device to continue sending audio data for a period without requiring the user to say the wake word again (Claim 1). For example, if you say "Alexa, what's the weather?" and it responds, the system might then listen for a follow-up like "What about tomorrow?" without you needing to say "Alexa" again. The system can also stop this "attention span" if the command type suggests it's no longer needed, such as after starting media playback (Claim 2).

What it doesn't cover

• —Voice assistants that always require a wake word for every single command.
• —Systems that keep listening indefinitely without a time threshold or specific command type trigger.
• —Devices that decide to keep listening on their own, rather than being explicitly instructed by a server (Claim 1).
• —Systems that only listen for follow-up commands if the user has explicitly enabled a general "continuous listening" mode, rather than based on the type of the previous command (Claim 1).
• —Systems that process all subsequent audio as commands without first determining if it represents speech intended for processing (Claim 4).

The clever bit

The novelty lies in the system intelligently deciding when to extend its listening period without a wake word, based on the type of command just given. Instead of always requiring the wake word or always listening for a fixed period, it makes a context-aware decision.

Why it matters

This patent addresses a common frustration with voice assistants: constantly repeating the wake word. By allowing for a brief "attention span," it makes interactions feel more natural and conversational. This improved user experience is crucial for the widespread adoption and daily use of smart speakers and other voice-controlled devices, making them more integrated into homes and workflows.

Real-world examples

• 1.Amazon Alexa's "Follow-Up Mode"
• 2.Google Assistant's "Continued Conversation"
• 3.Apple Siri's follow-up questions
• 4.Most modern smart speaker interactions