How Voice Assistants Recognize Who is Talking
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.
Original patent title: “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. Granted to Amazon Technologies in 2022 with 22 claims and 1 forward citation, and it is expected to expire in 2039.
Coverage
What does this patent actually cover?
The system first captures a sample of a user's voice, called "first audio data," during an initial setup or when a wake word is spoken (ClaimclaimA numbered sentence at the end of a patent that legally defines what the inventor owns. The most important section.Read more → 1). From this, it creates a unique "reference feature vector" that represents that user's voice (Claim 1). Later, when new "second audio data" comes in, the system compares it against this stored reference using a "trained model," like a neural network (Claim 1). It then figures out which parts of the new audio match the original speaker and which do not. For example, if a child says "Alexa, play music" and then the parent says "Alexa, stop," the system would identify the parent's voice as matching the reference and execute the "stop" command, while ignoring the child's voice if it doesn't match the reference. It only processes commands from the recognized speaker, "excluding" other voices (Claim 1).
The gap
What does this patent NOT cover?
- Does not cover systems that identify any speaker, only those that compare against a pre-determined reference speaker.
- Does not cover systems that authenticate a speaker using a password or passphrase, as it focuses on voice characteristics.
- Does not cover ignoring speech based on content (e.g., profanity filters), only based on speaker identity.
- Does not cover systems that perform speech recognition on all incoming audio regardless of speaker, as it specifically "excludes" non-matching speech from command processing.
These exclusions are unique to PatentBrief — derived from the actual claim language, not patent-office boilerplate.
Key facts
What made this novel
The noveltynoveltyThe requirement that an invention be different from anything publicly known before its priority date.Read more → lies in using a "reference feature vector" derived from a specific speaker's voice to filter incoming audio before full speech recognition, ensuring that only desired speech from the intended speaker is processed for commands. This improves efficiency and accuracy by ignoring irrelevant voices.
The Patent Drawing
Schematic visualization of the patent's claim structure. Hand-drawn diagrams in progress for each landmark patent.
Where you've seen this
Real-world examples
Amazon Echo devices (Alexa)
Google Assistant's Voice Match
Apple HomePod (Siri)
Smart speakers with personalized voice recognition
Why it matters
The bigger picture
This technology is crucial for personalizing voice assistant experiences and enhancing privacy. By ensuring that a voice assistant like Alexa only responds to its designated user, it prevents unintended interactions from other household members or background conversations. This allows for features like personalized music profiles or access to sensitive information only by the account holder.
Filed
June 11, 2019
Granted
November 29, 2022
Market context
Who's building on this
Companies in this space
Amazon Technologies Inc. continues to develop and implement this type of speaker recognition technology in its Alexa-enabled devices. Other major players in the voice assistant space, such as Google with Google Assistant and Apple with Siri, also employ similar techniques to personalize user interactions and improve security.
Market impact
This technology has significantly enhanced the user experience for voice-controlled devices, moving them beyond simple command recognition to more personalized and secure interactions. It enabled the widespread adoption of multi-user smart speakers and allowed for individual profiles, preventing unauthorized access to personal information or services.
Claim 1 — Plain English
What this patent covers
The system first captures a sample of a user's voice, called "first audio data," during an initial setup or when a wake word is spoken (Claim 1). From this, it creates a unique "reference feature vector" that represents that user's voice (Claim 1). Later, when new "second audio data" comes in, the system compares it against this stored reference using a "trained model," like a neural network (Claim 1). It then figures out which parts of the new audio match the original speaker and which do not. For example, if a child says "Alexa, play music" and then the parent says "Alexa, stop," the system would identify the parent's voice as matching the reference and execute the "stop" command, while ignoring the child's voice if it doesn't match the reference. It only processes commands from the recognized speaker, "excluding" other voices (Claim 1).
The clever bit
The novelty lies in using a "reference feature vector" derived from a specific speaker's voice to filter incoming audio before full speech recognition, ensuring that only desired speech from the intended speaker is processed for commands. This improves efficiency and accuracy by ignoring irrelevant voices.
What it does not cover
- Does not cover systems that identify any speaker, only those that compare against a pre-determined reference speaker.
- Does not cover systems that authenticate a speaker using a password or passphrase, as it focuses on voice characteristics.
- Does not cover ignoring speech based on content (e.g., profanity filters), only based on speaker identity.
- Does not cover systems that perform speech recognition on all incoming audio regardless of speaker, as it specifically "excludes" non-matching speech from command processing.
Patent timeline
Application submitted to the patent office
Application published, typically 18 months after filing
Patent officially issued
Patent enters public domain
PatentBrief Score
Impact Score
Strong
Citation count
6/40
Early citations
Claim breadth
15/20
Broad claimsclaimsThe numbered statements at the end of a patent that legally define what the inventor owns.Read more →
Recency
20/20
Granted within 5 years
Assignee scale
20/20
Major company or institution
PatentBrief Impact Score — based on citation count, claim breadth, recency, and assignee scale. Not a legal assessment.
Heuristic Value Estimate
What this patent might be worth
$88K – $281K
Midpoint $176K · 12.8 yr remaining · industry ×1.5
Heuristic only — blends forward/backward citation counts, claim scope, time remaining, litigation history, and CPC-derived industry baseline. Real valuations need a professional appraisal.
Claim text not yet imported for this patent
The original legal language
Original claims
22 claims as filed with the patent office.
Concepts involved
Citations
Patent lineage
Cite this patent
Maas, R., Parthasarathi, S. H. K., Hoffmeister, B., & King, B. (2022). How Voice Assistants Recognize Who is Talking (U.S. Patent No. 11,514,901). U.S. Patent and Trademark Office. https://patentbrief.org/patent/us/11514901/anchored-speech-detection-and-speech-recognition
Auto-generated from the patent record. Double-check author order and the issue date against the official USPTO document before submitting.
Embed
Add this patent to your site
Drop this plain-English patent card into any blog post or article — free, no signup. It always links back to the full breakdown here.
<div data-patentlens-widget data-patent-number="US11514901"></div> <script src="https://patentbrief.org/embed.js" async></script>
Stay in the loop
Get a weekly digest of new patents.
One email per week. No spam. Unsubscribe anytime.
Keep exploring
Related patents you should know
US 4683195 · 1987
How to Make Billions of Copies of a DNA Segment
This patent describes the Polymerase Chain Reaction (PCR), a method to rapidly create many copies of a specific piece of DNA or RNA, enabling its detection and analysis.
Cetus Corp
US 8697359 · 2014
How to Edit Genes in Human Cells Using an Engineered CRISPR System
This patent describes an engineered CRISPR-Cas9 system for precisely cutting DNA in eukaryotic cells to change how genes work, opening the door for gene editing in complex organisms.
Massachusetts Institute of Technology
US 7657849 · 2010
How the iPhone's Slide-to-Unlock Gesture Works
Apple's 2010 patent describes unlocking a device by dragging a specific graphical image across the touchscreen along a predefined path, a gesture that became iconic with the original iPhone.
Apple Inc
US 4733665 · 1988
How Doctors Implant a Permanent Stent Using a Balloon
This patent describes the method for placing a permanent, expandable wire mesh tube inside a blood vessel or other body tube using a balloon-tipped catheter to widen it and keep it open.
Expandable Grafts Partnership
US 4965188 · 1990
How to Make Many Copies of a DNA Piece with Heat
This patent describes the Polymerase Chain Reaction (PCR) method, a technique to make millions of copies of a specific DNA segment using a heat-resistant enzyme and repeated temperature changes.
Cetus Corp
US 4235871 · 1980
How to Encapsulate Active Materials in Lipid Bubbles Efficiently
This patent describes a method for trapping biologically active substances inside tiny, multi-layered fat bubbles called liposomes, using a specific water-in-oil emulsion and gel-forming process to improve how much material gets captured.
Individual
Semantically similar
You might also find these interesting
US 11361763 · 2022 · Amazon Technologies
How Smart Speakers Know You're Talking to Them After a Command
US 20220189458 · Amazon Technologies
How Wearable Devices Use Location and Biometrics to Know Who You Are
US 10276149 · 2019 · Amazon Technologies
How Voice Assistants Change Their Speech Based on How You Talk
US 9965247 · 2018 · Sonos Inc
How Sonos Speakers Use Personalized Wake Words to Recognize Different Users
More to explore
More in Consumer Electronics
US 7657849 · 2010 · Apple Inc
How the iPhone's Slide-to-Unlock Gesture Works
US 7479949 · 2009 · Apple Inc
How Touchscreens Understand Your Finger Swipes and Scrolls
US 4528643 · 1985 · FPDC Inc
How Stores Make Custom Products On-Demand with Remote Approval
US 7469381 · 2008 · Apple Inc
How Touchscreens Show and Snap Back When You Scroll Past an Edge
New to patents?
Common Questions
Frequently Asked Questions
What does How Voice Assistants Recognize Who is Talking cover?
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.
Who owns patent US 11514901?
Amazon Technologies owns this patent, granted in 2022.
When does this patent expire?
This patent is expected to expire on June 11, 2039, when the invention enters the public domain.
What is patent US 11514901 cited by?
This patent has been cited by 1 later patents that build on its ideas.
What problem does this patent solve?
This technology is crucial for personalizing voice assistant experiences and enhancing privacy. By ensuring that a voice assistant like Alexa only responds to its designated user, it prevents unintended interactions from other household members or background conversations. This allows for features like personalized music profiles or access to sensitive information only by the account holder.
What does this patent NOT cover?
Does not cover systems that identify any speaker, only those that compare against a pre-determined reference speaker.
Same assignee
More from Amazon Technologies
Patent monitoring