The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
Aug. 12, 2025

Filed:

Feb. 14, 2024
Applicant:

Roblox Corporation, San Mateo, CA (US);

Inventors:

Morgan Samuel Mcguire, Waterloo, CA;

Tom Sanocki, San Mateo, CA (US);

Assignee:

Roblox Corporation, San Mateo, CA (US);

Attorney:
Primary Examiner:
Assistant Examiner:
Int. Cl.
CPC ...
G06F 21/62 (2013.01); G06T 13/20 (2011.01); G06T 13/40 (2011.01); G10L 13/033 (2013.01); G10L 13/10 (2013.01); G10L 17/06 (2013.01);
U.S. Cl.
CPC ...
G06F 21/6245 (2013.01); G06T 13/205 (2013.01); G06T 13/40 (2013.01); G10L 13/0335 (2013.01); G10L 13/10 (2013.01); G10L 17/06 (2013.01);
Abstract

Some implementations relate to methods, systems, and computer-readable media to reproduce a voice stream with removed personally identifiable information (PII). An original voice stream is received from a user by a hardware processor. The original voice stream is converted into text using a machine learning (ML) voice transcription model. Then, the text is used for generating an anonymized voice stream corresponding to the text having similar auditory properties to the original voice stream other than PII using a machine learning (ML) voice synthesis model. The similar properties are determined using metadata corresponding to the original voice stream. The metadata may be obtained by analyzing acoustic characteristics of the original voice stream. The metadata may include volume changes and pitch frequency changes stored as metadata annotations associated with tokens in the text as key-value pairs. The generation may use the metadata annotations to determine the similar audio properties.


Find Patent Forward Citations

Loading…