/Patent Tracker
SamsungPatent applicationAudio & voiceInterest 6/10

Samsung patents voice check that matches spoken words to text

Patent drawing
Patent drawing from the official filing.

Samsung describes a system that turns text into a synthetic voice and creates a digital fingerprint, or embedding, of that sound. When a user speaks, the device creates a second fingerprint and compares it to the first to verify if the spoken words match the original text. If they match, the device performs a specific action linked to that text.

Why it mattersThis could allow devices to verify that a user is actually saying a specific phrase before executing a command, potentially adding a layer of security or confirmation for voice-controlled actions.

In the filing’s own words

An electronic apparatus is disclosed. The electronic apparatus includes memory storing at least one instruction and one or more processors connected to the memory and configured to execute the at least one instruction, and the one or more processors are configured to obtain a synthetic voice based on the text, obtain a first embedding and store the first embedding in the memory based on the synthetic voice, based on an uttered voice of a user being received, obtain a second embedding based on the uttered voice, determine whether the uttered voice corresponds to the text based on a first similarity between the first embedding and the second embedding, and based on the uttered voice corresponding to the text, perform an operation based on the text.

What exactly they claim (claim 1)

1. An electronic apparatus comprising: memory storing at least one instruction; and one or more processors configured to execute the at least one instruction stored in the memory, wherein the one or more processors are configured to: based on text, obtain a synthetic voice, wherein the text is based on a user input; obtain a first embedding, based on the synthetic voice, and store the first embedding in the memory; based on an uttered voice of a user being received, obtain a second embedding based on the uttered voice of the user; based on a first similarity between the first embedding and the second embedding, determine whether the uttered voice corresponds to the text; and based on the uttered voice corresponding to the text, perform an operation based on the text.

Facts

Company
Samsung (SAMSUNG ELECTRONICS CO., LTD.)
Official title
ELECTRONIC APPARATUS USING SYNTHETIC VOICE OBTAINED FROM TEXT AND CONTROL METHOD THEREOF
Publication number
US20260321245A1
Application number
19698436
Filed
Jun 4, 2026
Published
Oct 15, 2026
Inventors
4
Claims
20

Classified under

G10L 13/10 Physics & computingG10L 13/027 Physics & computingG10L 15/063 Physics & computingG10L 15/22 Physics & computingG10L 21/0208 Physics & computingG10L 21/0316 Physics & computing
Read the full filing (official PDF) ↗ Open in the Patent Tracker

More from Samsung in Audio & voice

Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.