# 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. - **Patent:** US 10847149 - **Original title:** Speech-based attention span for voice user interface - **Owner:** Amazon Technologies - **Granted:** 2020 - **Status:** Active - **Times cited:** 87 - **Field:** consumer_electronics, software, telecommunications, ai_ml ## What it does 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 does NOT 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. ## 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 ## 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. ## Frequently asked questions ### What does How Voice Assistants Listen for More Commands Without a Wake Word cover? 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. ### Who owns patent US 10847149? Amazon Technologies owns this patent, granted in 2020. ### When does this patent expire? This patent is expected to expire on September 1, 2037, when the invention enters the public domain. ### What is patent US 10847149 cited by? This patent has been cited by 87 later patents that build on its ideas. ### What problem does this patent solve? 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. ### What does this patent NOT cover? Voice assistants that always require a wake word for every single command. **Full plain-English explainer:** https://patentbrief.org/patent/us/10847149/speech-based-attention-span-for-voice-user-interface **Original patent:** https://patents.google.com/patent/US10847149 --- _Source: PatentBrief — https://patentbrief.org. Patent facts are from public records; the plain-English explanation is PatentBrief's._ ## Related patents Semantically similar inventions in the PatentBrief corpus: - [How Smart Speakers Know You're Talking to Them After a Command](https://patentbrief.org/patent/us/11361763/detecting-system-directed-speech) — This patent describes how a smart speaker system can tell if follow-up speech is meant for it, even without a "wake word," by analyzing voice activity and partial speech recognition results using an AI model. - [How Voice Assistants Distinguish Speakers After a Wakeword](https://patentbrief.org/patent/us/10923111/speech-detection-and-speech-recognition) — This patent describes a method for voice assistants to better understand who is speaking after a 'wakeword' by comparing voice characteristics to improve speech recognition accuracy, especially in multi-speaker environments. - [How Voice Assistants Know When You've Finished Talking](https://patentbrief.org/patent/us/10121471/language-model-speech-endpointing) — This patent describes a method for speech recognition systems to accurately detect the end of a spoken phrase by considering multiple interpretations of the audio and how much silence each interpretation suggests. - [How Voice Assistants Recognize Who is Talking](https://patentbrief.org/patent/us/11514901/anchored-speech-detection-and-speech-recognition) — This patent describes a system that uses a recorded voice sample to identify if new speech comes from the same person, allowing voice assistants to only respond to specific users. - [How a Digital Assistant Launches Apps Using Your Voice](https://patentbrief.org/patent/us/9548050/continuity-handoff) — This patent describes how a digital assistant like Siri uses your spoken words and understanding of your conversation to figure out what you want and launch the right app.