IP Library › Granted Patent US 12,579,700
Granted Patent B2
US 12,579,700 · App. 18/202,631 · Granted Mar 17, 2026

Methods of impersonation in streaming media

Inventors: Zhiyun Li (Kenmore, WA); Reda Harb (Issaquah, WA); Tao Chen (Palo Alto, CA)
Assignee: Adeia Guides Inc.
G06T11/00G06F3/0482G06T7/11G06T2200/16G06T2200/24G06T2207/10016G06T2207/30201
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,579,700
App. No.
18/202,631
Granted
Mar 17, 2026
Kind
B2
Abstract

Disclosed is a method comprising receiving a request to view a content item comprising a first character having a first character representation, accessing permissions regarding replacement of the first character representation, determining whether the permissions allow replacement of the first character representation, in response to the determining, generating for display an option to replace the first character representation in the content item, receiving a request to replace in the content item the first character representation via selection of the displayed option, obtaining a representation of a source individual, and generating for display a modified version of the content, wherein the first character representation is replaced with the representation of the source individual in at least a portion of the content item.

Claims (85)

1 . A method comprising:

receiving a request to view a content item comprising a first character having a first character representation;

accessing permissions regarding replacement of the first character representation;

determining whether the permissions allow replacement of the first character representation;

in response to the determining, generating for display an option to replace the first character representation in the content item;

receiving a request to replace in the content item the first character representation via selection of the displayed option;

obtaining a representation of a source individual; and

generating for display a modified version of the content, wherein the first character representation is replaced with the representation of the source individual in at least a portion of the content item.

2 . The method of claim 1 further comprising:

in response to receiving the request, accessing a manifest file of the modified version of the content comprising the permissions regarding replacement of the first character representation wherein the manifest file further comprises a network location of at least one modifiable segment of the first content item; and

wherein the generating for display the modified version of the content comprises obtaining data from the network location of at least one modifiable segment of the first content item indicated by the manifest of the modified version of the content.

3 . The method of claim 2 , wherein the modifiable version is modified using the obtained representation of a source individual and stored at the network location after generating for display at least a portion of the modified version of the content.

4 . The method of claim 2 , further comprising:

beginning to generate for display the modified version of the content item using a manifest file of the content item; and

after the accessing manifest file of the modified version of the content, continuing to generate for display the modified version of the content item using the manifest file of the modified version of the content.

5 . The method of claim 1 wherein:

the source individual has a familial relationship with a second source individual;

the first character has a familial relationship with a second character, the second character having a second character representation; and

the familial relationship between the first character and second character is the same familial relationship as the familial relationship between the source individual and second source individual; and

wherein the method further comprises:

accessing permissions regarding replacement of the second character representation;

determining whether the permissions allow replacement of the second character representation;

in response to the determining whether the permissions allow replacement of the second character representation, generating for display a second option to replace the second character representation in the content item based on the familial relationship;

receiving a request to replace in the content item the second character representation based on the familial relationship via selection of the displayed second option;

obtaining a representation of the second source individual;

generating for display a modified version of the content, wherein the second character representation is replaced with the representation of the second source individual in at least a portion of the content item.

6 . The method of claim 1 wherein the content item further comprises a second character having a second character representation, the method further comprising:

accessing permissions regarding replacement of the second character representation;

determining whether the permissions allow replacement of the second character representation;

in response to the determining, determining that the source individual more closely resembles the first character than the second character; and

wherein the generating for display an option to replace the first character representation in the content item is further in response to determining that the source individual more closely resembles the first than the second character.

7 . The method of claim 1 further comprising receiving a request to present the modified version of the content for simultaneous display to a group of users and wherein the source individual is selected from the group of users.

8 . The method of claim 1 further comprising:

receiving, using a camera or microphone coupled to a user device, input representing the source individual; and

wherein the representation of the source individual is created using the input representing the source individual.

9 . The method of claim 8 further comprising:

directing the source individual to perform an action;

capturing the action via the camera or microphone; and

wherein the representation of the source individual is created using the capturing of the action.

10 . The method of claim 1 further comprising:

identifying, using information received by a camera or microphone at least one audience member of the modified version of the content; and

wherein the source individual is the at least one audience member.

11 . A system comprising:

processing circuitry configured to:

receive a request to view a content item comprising a first character having a first character representation;

access permissions regarding replacement of the first character representation;

determine whether the permissions allow replacement of the first character representation;

in response to the determining, generate for display an option to replace the first character representation in the content item;

receive a request to replace in the content item the first character representation via selection of the displayed option;

obtain a representation of a source individual; and

generate for display a modified version of the content, wherein the first character representation is replaced with the representation of the source individual in at least a portion of the content item.

12 . The system of claim 11 , the processing circuitry further configured to:

in response to receiving the request, access a manifest file of the modified version of the content comprising the permissions regarding replacement of the first character representation wherein the manifest file further comprises a network location of at least one modifiable segment of the first content item; and

wherein to generate for display the modified version of the content comprises to obtain data from the network location of at least one modifiable segment of the first content item indicated by the manifest of the modified version of the content.

13 . The system of claim 12 , wherein the modifiable version is modified using the obtained representation of a source individual and stored at the network location after generating for display at least a portion of the modified version of the content.

14 . The system of claim 12 , the processing circuitry further configured to:

begin to generate for display the modified version of the content item using a manifest file of the content item; and

after the accessing manifest file of the modified version of the content, continue to generate for display the modified version of the content item using the manifest file of the modified version of the content.

15 . The system of claim 11 wherein:

the source individual has a familial relationship with a second source individual;

the first character has a familial relationship with a second character, the second character having a second character representation; and

the familial relationship between the first character and second character is the same familial relationship as the familial relationship between the source individual and second source individual; and

wherein the processing circuitry is further configured to:

access permissions regarding replacement of the second character representation;

determine whether the permissions allow replacement of the second character representation;

in response to determining whether the permissions allow replacement of the second character representation, generate for display a second option to replace the second character representation in the content item based on the familial relationship;

receive a request to replace in the content item the second character representation based on the familial relationship via selection of the displayed second option;

obtain a representation of the second source individual; and

generate for display a modified version of the content, wherein the second character representation is replaced with the representation of the second source individual in at least a portion of the content item.

16 . The system of claim 11 wherein the content item further comprises a second character having a second character representation, the processing circuitry further configured to:

access permissions regarding replacement of the second character representation;

determine whether the permissions allow replacement of the second character representation;

in response to the determining, determine that the source individual more closely resembles the first character than the second character; and

wherein to generate for display an option to replace the first character representation in the content item is further in response to determining that the source individual more closely resembles the first than the second character.

17 . The system of claim 11 , the processing circuitry further configured to receive a request to present the modified version of the content for simultaneous display to a group of users and wherein the source individual is selected from the group of users.

18 . The system of claim 11 , the processing circuitry further configured to:

receive, using a camera or microphone coupled to a user device, input representing the source individual; and

wherein the representation of the source individual is created using the input representing the source individual.

19 . The system of claim 18 , the processing circuitry further configured to:

direct the source individual to perform an action;

capture the action via the camera or microphone; and

wherein the representation of the source individual is created using the capturing of the action.

20 . The system of claim 11 , the processing circuitry further configured to

identify, using information received by a camera or microphone at least one audience member of the modified version of the content; and

wherein the source individual is the at least one audience member.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 25, 2023
From: LI, ZHIYUN; HARB, REDA; CHEN, TAO
To: ADEIA GUIDES INC.
Reel/Frame 064703/0649 →
Continuity (1)
Related Publication 20240394929A1 · Nov 28, 2024
References Cited (27)
US 20130268490A1 · Keebler · 2013 [cited by examiner]
US 20200159870A1 · Bowen · 2020 [cited by examiner]
US 20220398538A1 · Jakobsson · 2022 [cited by examiner]
“Disney's face-swap technology is as impressive as it is unsettling,” Engadget, https://www.engadget.com/disneys-faceswap-technology-is-as-impressive-as-it-is-unsettling-123524432.html, retrieved from the internet on Au… [cited by applicant]
Aquilina, “Roadrunner director used audio deepfake to recreate Anthony Bourdain's voice in documentary,” Entertainment Weekly magazine, pp. 1-8 (2021). [cited by applicant]
Bass, “New York's New Right of Publicity Law: Protecting Performers and Producers,” NYSBA, pp. 1-13 (2021). [cited by applicant]
Ferraro, “Texas Law Could Signal More State, Federal Deepfake Bans,” Law 360, pp. 1-3 (2019). [cited by applicant]
https://www.deepswap.ai/, retrieved from internet Aug. 15, 2023. [cited by applicant]
https://www.d-id.com/, retrieved from the internet on Aug. 15, 2023. [cited by applicant]
https://www.youtube.com/watch?v=0sR1rU3gLzQ, retrieved from the internet Aug. 15, 2023. [cited by applicant]
Hu et al., “SVSNet: An End-to-end Speaker Voice Similarity Assessment Model,” https://arxiv.org/pdf/2107.09392.pdf, 5 pages (2022). [cited by applicant]
Jia et al., “Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis,” 32nd Conference on Neural Information Processing Systems (NeurIPS), https://arxiv.org/pdf/1806.04558.pdf, 15 pages (201… [cited by applicant]
Kelly et al., “Identifying perceptually similar voices with a speaker recognition system using auto-phonetic features,” https://www.oxfordwaveresearch.com/wp-content/uploads/2019/03/OxfordWaveResearch-Kellyetal-S16_show… [cited by applicant]
Lalla et al., “Artificial intelligence: deepfakes in the entertainment industry,” WIPO Magazine, pp. 1-7 (2022). [cited by applicant]
Li et al., “Automatic Recognition of Smiling and Neutral Facial Expressions,” 2010 IEEE Dicta, https://ieeexplore.ieee.org/document/5692624, abstract only, 4 pages. [cited by applicant]
Li et al., “FaceShifter: Towards High Fidelity and Occlusion Aware Face Swapping,” https://arxiv.org/pdf/1912.13457.pdf, 11 pages (2020). [cited by applicant]
List of video games based on films—Wikipedia, https://en.wikipedia.org/wiki/List_of_video_games_based_on_films, retrieved from the internet on Aug. 15, 2023. [cited by applicant]
Ma et al., “Real-time Face Video Swapping from a Single Portrait,” I3D 2020. http://graphics.cs.uh.edu/wp-content/papers/2020/2020-13D-RealTimeFaceSwapping.pdf, 10 pages. [cited by applicant]
Moon, “Warner Bros. ‘Reminiscence’ promo uses deepfake tech to put you in the trailer,” Engadget. retrieved from the Internet Jul. 25, 2023. [cited by applicant]
Perez, “MyHeritage and D-ID partner to bring photos to life with both animations and voice,” TechCrunch, pp. 1-19 (2022). [cited by applicant]
Reminiscence—Now Playing in Theatres & HBO Max (bannisterandassociates.com) p. 1 retrieved from internet Jul. 25, 2023. [cited by applicant]
Riparbelli, “Snoop Dogg,” Synthesia, pp. 1-4 (2023). [cited by applicant]
Sadovnik et al., “Finding your Lookalike: Measuring Face Similarity Rather than Face Identity,” https://openaccess.thecvf.com/content_cvpr_2018_workshops/papers/w48/Sadovnik_Finding_Your_Lo okalike_CVPR_2018_paper.pdf, … [cited by applicant]
Tandel et al., “Voice Recognition and Voice Comparison using Machine Learning Techniques: A Survey,” https://ieeexplore.ieee.org/document/9074184, Abstract only, 4 pages (2020). [cited by applicant]
Thies et al., “Face2Face: Real-time Face Capture and Reenactment of RGB Videos,” TUM Visual Computing & Artificial Intelligence, http://niessnerlab.org/projects/thies2016face.html ,2 page (2023). [cited by applicant]
Tom Cruise Hyper-realistic DeepFake, https://www.youtube.com/watch?v=t5pufwWX540, retrieved from the internet on Aug. 15, 2023. [cited by applicant]
Yuan et al., “Improving Zero-Shot Voice Style Transfer via Disentangled Representation Learning,” https://arxiv.org/abs/2103.09420, 17 pages (2021). [cited by applicant]