IP Library › Granted Patent US 12,614,541
Granted Patent B2
US 12,614,541 · App. 18/496,313 · Granted Apr 28, 2026

Systems and methods for machine-learning based multi-lingual pronunciation generation

Inventors: Pheobe Sun (London, GB); Alexandru-Petre Cazan (Mumbai Suburban, IN); Ruibo Shi (London, GB); Sean Moran (London, GB)
Assignee: JPMORGAN CHASE BANK, N.A.
G10L13/047H04L12/1813
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 12,614,541
App. No.
18/496,313
Granted
Apr 28, 2026
Kind
B2
Abstract

Systems and methods for machine-learning based multi-lingual pronunciation generation are disclosed. A method for machine-learning based multi-lingual pronunciation generation may include: (1) training a language origin prediction machine learning model; (2) training a pronunciation generator machine learning model; (3) receiving, by a pronunciation computer program, a word for pronunciation guidance; (4) predicting, by the pronunciation computer program and using the trained language origin prediction machine learning model, a language origin of the word; (5) predicting, by the pronunciation computer program and using the trained pronunciation generator machine learning model and the language origin, a syllable-by-syllable pronunciation for the word; and (6) returning, by the pronunciation computer program, the syllable-by-syllable pronunciation.

Claims (29)

1 . A method for machine-learning based multi-lingual pronunciation generation, comprising:

training a language origin prediction machine learning model;

training a plurality of pronunciation generator machine learning models, wherein each of the trained pronunciation generator machine learning model is specific to a language origin;

receiving, by a pronunciation computer program, a word for pronunciation guidance;

predicting, by the pronunciation computer program and using the trained language origin prediction machine learning model, a language origin of the word;

selecting, by the pronunciation computer program, one of the plurality of trained pronunciation generator machine learning models for the predicted language origin;

predicting, by the pronunciation computer program and using the selected trained pronunciation generator machine learning model, a syllable-by-syllable pronunciation for the word; and

returning, by the pronunciation computer program, the syllable-by-syllable pronunciation.

2 . The method of claim 1 , wherein the word is a name.

3 . The method of claim 1 , wherein the language origin prediction machine learning model and/or the pronunciation generator machine learning model are trained using supervised learning.

4 . The method of claim 1 , further comprising:

receiving, by the pronunciation computer program, feedback; and

re-training the language origin prediction machine learning model and/or the pronunciation generator machine learning model using the feedback.

5 . The method of claim 1 , wherein the word is received at an application executed by a user electronic device that is in communication with the pronunciation computer program.

6 . The method of claim 5 , wherein the application outputs audio of the syllable-by-syllable pronunciation.

7 . The method of claim 5 , wherein the application outputs text of the syllable-by-syllable pronunciation.

8 . The method of claim 1 , wherein the pronunciation computer program is integrated into a videoconferencing computer program.

9 . A system, comprising:

a trained language origin prediction machine learning model;

a plurality of trained pronunciation generator machine learning models, wherein each of the trained pronunciation generator machine learning model is specific to a language origin; and

an electronic device executing a pronunciation computer program that is configured to receive a word for pronunciation guidance, to predict using the trained language origin prediction machine learning model, a language origin of the word, to select one of the plurality of trained pronunciation generator machine learning models for the predicted language origin, to predict, using the selected trained pronunciation generator machine learning model, a syllable-by-syllable pronunciation of the word, and to output the syllable-by-syllable pronunciation.

10 . The system of claim 9 , wherein the word is a name.

11 . The system of claim 9 , wherein the trained language origin prediction machine learning model and/or the trained pronunciation generator machine learning model are trained using supervised learning.

12 . The system of claim 9 , wherein the pronunciation computer program is further configured to receive feedback and to retrain the trained language origin prediction machine learning model and/or the trained pronunciation generator machine learning model using the feedback.

13 . The system of claim 9 , further comprising:

a user electronic device executing an application, wherein application is configured to receive the word.

14 . The system of claim 13 , wherein the application outputs audio of the syllable-by-syllable pronunciation on a speaker.

15 . The system of claim 13 , wherein the application outputs text of the syllable-by-syllable pronunciation on a display.

16 . The system of claim 9 , wherein the pronunciation computer program is integrated into a videoconferencing computer program.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 24, 2026
From: SUN, PHEOBE; CAZAN, ALEXANDRU-PETRE; SHI, RUIBO; MORAN, SEAN
To: JPMORGAN CHASE BANK, N.A.
Reel/Frame 073874/0185 →
Continuity (2)
Provisional Application 63382823 · Nov 8, 2022
Related Publication 20240153485A1 · May 9, 2024
References Cited (103)
US 6708150B1 · Hirayama · 2004 [cited by examiner]
US 7092870B1 · Chen · 2006 [cited by examiner]
US 7292980B1 · August · 2007 [cited by examiner]
US 7487096B1 · Cox · 2009 [cited by examiner]
US 8408913B2 · Palacios · 2013 [cited by examiner]
US 8510112B1 · Conkie · 2013 [cited by examiner]
US 9275637B1 · Salvador · 2016 [cited by examiner]
US 9471566B1 · Zhang · 2016 [cited by examiner]
US 9916295B1 · Crawford · 2018 [cited by examiner]
US 11024199B1 · Treves · 2021 [cited by examiner]
US 11810548B2 · Kim · 2023 [cited by examiner]
US 12027059B1 · Bloch · 2024 [cited by examiner]
US 20020013707A1 · Shaw · 2002 [cited by examiner]
US 20020086269A1 · Shpiro · 2002 [cited by examiner]
US 20030170595A1 · Thompson · 2003 [cited by examiner]
US 20030225580A1 · Lin · 2003 [cited by examiner]
US 20030232312A1 · Newsom · 2003 [cited by examiner]
US 20050071165A1 · Hofstader · 2005 [cited by examiner]
US 20050159954A1 · Chu · 2005 [cited by examiner]
US 20050203738A1 · Hwang · 2005 [cited by examiner]
US 20050203739A1 · Hwang · 2005 [cited by examiner]
US 20050256715A1 · Okimoto · 2005 [cited by examiner]
US 20060003297A1 · Wiig · 2006 [cited by examiner]
US 20060100871A1 · Choi · 2006 [cited by examiner]
US 20060110711A1 · Julia · 2006 [cited by examiner]
US 20060110712A1 · Julia · 2006 [cited by examiner]
US 20070124133A1 · Wang · 2007 [cited by examiner]
US 20070239455A1 · Groble · 2007 [cited by examiner]
US 20070255570A1 · Annaz · 2007 [cited by examiner]
US 20080052064A1 · Kim · 2008 [cited by examiner]
US 20080120108A1 · Soong · 2008 [cited by examiner]
US 20090048843A1 · Nitisaroj · 2009 [cited by examiner]
US 20090258333A1 · Yu · 2009 [cited by examiner]
US 20090291419A1 · Uekawa · 2009 [cited by examiner]
US 20090295734A1 · Hendrickson · 2009 [cited by examiner]
US 20110093259A1 · Saffer · 2011 [cited by examiner]
US 20110238412A1 · Ezzat · 2011 [cited by examiner]
US 20110282650A1 · Jennings · 2011 [cited by examiner]
US 20120034581A1 · Chang · 2012 [cited by examiner]
US 20120164609A1 · Kehoe · 2012 [cited by examiner]
US 20120164611A1 · O · 2012 [cited by examiner]
US 20120290302A1 · Yang · 2012 [cited by examiner]
US 20120322034A1 · Renduchintala · 2012 [cited by examiner]
US 20130325448A1 · Levien · 2013 [cited by examiner]
US 20150106082A1 · Ge · 2015 [cited by examiner]
US 20150255069A1 · Adams · 2015 [cited by examiner]
US 20160133155A1 · Lee · 2016 [cited by examiner]
US 20160188727A1 · Waibel · 2016 [cited by examiner]
US 20160307453A1 · Pemba · 2016 [cited by examiner]
US 20160321953A1 · Kang · 2016 [cited by examiner]
US 20170154546A1 · Butler · 2017 [cited by examiner]
US 20170236447A1 · Stalling · 2017 [cited by examiner]
US 20170287356A1 · Stephen · 2017 [cited by examiner]
US 20170358293A1 · Chua · 2017 [cited by examiner]
US 20180075844A1 · Kim · 2018 [cited by examiner]
US 20180189259A1 · Merl · 2018 [cited by examiner]
US 20180190269A1 · Lokeswarappa · 2018 [cited by examiner]
US 20180268728A1 · Burdis · 2018 [cited by examiner]
US 20180268732A1 · Thiel · 2018 [cited by examiner]
US 20180330715A1 · Lee · 2018 [cited by examiner]
US 20180330729A1 · Golipour · 2018 [cited by examiner]
US 20180350345A1 · Naik · 2018 [cited by examiner]
US 20190013009A1 · Pinson · 2019 [cited by examiner]
US 20190066682A1 · Cheng · 2019 [cited by examiner]
US 20190115039A1 · Du · 2019 [cited by examiner]
US 20190189027A1 · Begert · 2019 [cited by examiner]
US 20190303797A1 · Javali · 2019 [cited by examiner]
US 20190341047A1 · Du · 2019 [cited by examiner]
US 20190363959A1 · Rice · 2019 [cited by examiner]
US 20200117713A1 · Ray · 2020 [cited by examiner]
US 20200260186A1 · Stachura · 2020 [cited by examiner]
US 20200342852A1 · Kim · 2020 [cited by examiner]
US 20210097976A1 · Chicote · 2021 [cited by examiner]
US 20210124803A1 · Alloh · 2021 [cited by examiner]
US 20210125602A1 · Hakata · 2021 [cited by examiner]
US 20210174789A1 · Hwang · 2021 [cited by examiner]
US 20210225198A1 · Cummings · 2021 [cited by examiner]
US 20210304771A1 · Lin · 2021 [cited by examiner]
US 20210319712A1 · Kim · 2021 [cited by examiner]
US 20210327431A1 · Stewart · 2021 [cited by examiner]
US 20210334299A1 · Sonntag · 2021 [cited by examiner]
US 20210350784A1 · Selvaggi · 2021 [cited by examiner]
US 20210407515A1 · Hermanns · 2021 [cited by examiner]
US 20220035867A1 · Tambi · 2022 [cited by examiner]
US 20220036759A1 · Proudfoot · 2022 [cited by examiner]
US 20220138420A1 · Tanaka · 2022 [cited by examiner]
US 20220138426A1 · Jung · 2022 [cited by examiner]
US 20220328034A1 · Tv · 2022 [cited by examiner]
US 20220351715A1 · Freed · 2022 [cited by examiner]
US 20220375453A1 · Zhang · 2022 [cited by examiner]
US 20220375456A1 · Yang · 2022 [cited by examiner]
US 20230115538A1 · Hoscilowicz · 2023 [cited by examiner]
US 20230223025A1 · Kawano · 2023 [cited by examiner]
US 20230298564A1 · Fang · 2023 [cited by examiner]
US 20230325421A1 · Kalekar · 2023 [cited by examiner]
US 20230386446A1 · Lahr · 2023 [cited by examiner]
US 20240013790A1 · Li · 2024 [cited by examiner]
US 20240021183A1 · Iriyama · 2024 [cited by examiner]
US 20240119862A1 · Zheng · 2024 [cited by examiner]
US 20240153484A1 · Rosenberg · 2024 [cited by examiner]
US 20250087190A1 · Iriyama · 2025 [cited by examiner]
US 20250285555A1 · Park · 2025 [cited by examiner]
US 20250349226A1 · Stephen · 2025 [cited by examiner]