IP Library Granted Patent US 12,437,673
Granted Patent B2
US 12,437,673 · App. 18/101,904 · Granted Oct 7, 2025

System and method for bidirectional automatic sign language translation and production

Inventors: Daryl Luciano Peralta (Metro Manila, PH); Shakira Arguelles (Rizal, PH); Williard Joshua Decena Jose (Metro Manila, PH)
Assignee: SAMSUNG ELECTRONICS CO., LTD.
G09B21/009G06T9/00G06T13/40G10L13/00
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 12,437,673
App. No.
18/101,904
Granted
Oct 7, 2025
Kind
B2
Abstract

An embodiment relates to a system and method for bidirectional automatic sign language translation and visualization. of the system includes at least two communication-capable devices for receiving and processing information from the system's input and/or output and showing the output of the system. At least two individuals are communicating with each other, both using different modes of communication such as sign language and spoken language. The individuals are able to utilize two separate computing devices, with the system installed or disposed, to translate the information the individuals are signing.

Claims (34)

1. A system for bidirectional automatic sign language translation and production, the system comprising:

at least one communication-capable device in communication with another communication-capable device;

at least one visual sensor disposed on the at least one communication-capable device for acquiring input visual feed;

at least one audio sensor disposed on the at least one communication-capable device for acquiring input audio feed;

at least one text interface disposed on the at one least communication-capable device for acquiring input text feed;

the at least one communication-capable device further comprising:

at least one visual display; and

at least one auditory display;

a translation block for processing the input visual feed, the translation block comprising:

an input processing module;

a frame encoder in communication with the input processing module;

a sequence encoder in communication with the frame encoder;

a word-level decoder in communication with the sequence encoder;

a sentence-level decoder in communication with the sequence encoder;

a text-to-speech module in communication with the sentence-level decoder; and

a first output processor in communication with the word-level decoder, the sentence-level decoder, and the text-to-speech module;

a production block for processing the audio feed and text feed, the production block comprising:

a speech recognition module;

an input processor in communication with the speech recognition module;

an input-to-pose generator in communication with the input processor the input-to-pose genera of figured to e f poses;

a pose sequence buffer in communication with the input-to-pose generator, the pose sequence buffer being configured to store the sequence of poses, check when the pose sequence buffer is empty, and generate an end-of-pose signal indicating an end of the sequence of poses in the pose sequence buffer; and

a second output processor in communication with the pose sequence buffer to receive the sequence of poses, the second output processor being configured to receive the end-of-pose signal;

wherein a production model in the production block and a translation model in the translation block are trained simultaneously by machine learning methods.

2. The system according to claim 1 , wherein the production block comprises a sign language identification method module for language identification.

3. The system according to claim 1 , wherein the at least one communication-capable device is in communication with the another communication-capable device through a communication protocol.

4. The system according to claim 1 , wherein a first output from the production model trains the translation model while a second output from the translation model trains the production model.

5. A method for bidirectional automatic sign language production, the method comprising:

receiving an audio feed;

converting the received audio feed into another data format for a sign language;

generating a sequence of poses to refer to the sign language having been translated from the audio feed;

storing the sequence of poses in a pose sequence buffer, wherein a check is performed to determine when the pose sequence buffer is empty, and wherein an end-of-pose signal is generated to indicate an end of the sequence of poses in the pose sequence buffer; and

displaying the sequence of poses as the sign language;

wherein machine learning methods are utilized to optimize generating the sequence of poses.

6. The method according to claim 5 , wherein the sequence of poses comprises photorealistic videos, 3D animated videos, or a combination of the photorealistic videos and the 3D animated videos.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 26, 2023
From: PERALTA, DARYL LUCIANO; ARGUELLES, SHAKIRA; JOSE, WILLIARD JOSHUA DECENA
To: SAMSUNG ELECTRONICS CO., LTD.
Reel/Frame 062501/0406 →
Priority Claims (1)
PH 12022050141 · Apr 4, 2022 · national
Continuity (2)
Continuation PCTKR2023000115 · Jan 4, 2023
Related Publication 20230316952A1 · Oct 5, 2023
References Cited (26)
US 10089901B2 · Jung et al. · 2018 [cited by applicant]
US 10289903B1 · Chandler · 2019 [cited by examiner]
US 10902219B2 · Natesan et al. · 2021 [cited by applicant]
US 10956725B2 · Menefee et al. · 2021 [cited by applicant]
US 20090012788A1 · Gilbert · 2009 [cited by examiner]
US 20130204605A1 · Illgner-Fehns · 2013 [cited by applicant]
US 20160042228A1 · Opalka et al. · 2016 [cited by applicant]
US 20170236450A1 · Jung · 2017 [cited by examiner]
US 20190138607A1 · Zhang · 2019 [cited by examiner]
US 20190279529A1 · Al-Gabri · 2019 [cited by examiner]
US 20200005028A1 · Gu · 2020 [cited by examiner]
US 20200075011A1 · Yao · 2020 [cited by applicant]
US 20200167556A1 · Kaur · 2020 [cited by examiner]
US 20210043110A1 · Jung · 2021 [cited by examiner]
US 20210174034A1 · Retek · 2021 [cited by examiner]
CN 110677639A · 2020 [cited by applicant]
CN 108256458B · 2020 [cited by applicant]
JP 2015169814A · 2015 [cited by applicant]
JP 2019124901A · 2019 [cited by applicant]
JP 2021196708A · 2021 [cited by applicant]
KR 20160109708A · 2016 [cited by applicant]
KR 102212298B1 · 2021 [cited by applicant]
KR 102318150B1 · 2021 [cited by applicant]
KR 102370993B1 · 2022 [cited by applicant]
Camgoz et al. “Sign Language Transformers: Joint End-to-end Sign Language Recognition and Translation”. arXiv:2003.13830v1 [cs.CV] Mar. 30, 2020 (Year: 2020). [cited by examiner]
International Search Report and Written Opinion for International Application No. PCT/KR2023/000115; International filing date Jan. 4, 2023; Date of Mailing Apr. 21, 2023; 9 Pages. [cited by applicant]