IP Library Granted Patent US 12,475,885
Granted Patent B2
US 12,475,885 · App. 17/965,958 · Granted Nov 18, 2025

Translation of voice commands using machine learning

Inventor: Rohit Pradeep Shetty (Bangalore, IN)
Assignee: Omnissa, LLC
G10L15/22G06F3/167G06F40/253G06F40/284G10L15/26G10L2015/223
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 12,475,885
App. No.
17/965,958
Granted
Nov 18, 2025
Kind
B2
Abstract

The present disclosure relates to translation of voice commands using machine learning. Command text corresponding to a voice command can be received, and at least one error can be identified in the command text. A comparison can be performed between the at least one error and at least one lexical pattern corresponding to a user associated with the voice command. Modified command text can be generated based at least in part on the comparison between the at least one error and the at least one lexical pattern. The modified command text can be determined to fail to comprise an additional error.

Claims (51)

1 . A system, comprising:

at least one computing device comprising a processor and a memory; and

machine-readable instructions stored in the memory that, when executed by the processor, cause the at least one computing device to at least:

receive command text corresponding to a voice command;

identify at least one error in the command text, the error comprising one or more words, phrases or grammatical units that are determined to be erroneous;

determine at least one lexical pattern corresponding to a user associated with the voice command based at least in part on at least one electronic message associated with the user;

perform a comparison between the at least one error and the at least one lexical pattern corresponding to the user associated with the voice command;

generate modified command text based at least in part on the comparison between the at least one error and the at least one lexical pattern; and

determine that the modified command text does not comprise any error.

2 . The system of claim 1 , wherein the machine-readable instructions that cause the at least one computing device to at least generate the modified command text based at least in part on the comparison between the at least one error and the at least one lexical pattern further cause the at least one computing device to at least substitute a grammatical unit corresponding to the at least one error for a grammatical unit corresponding to the at least one lexical pattern within the command text.

3 . The system of claim 1 , wherein the at least one computing device is at least one first computing device, and the machine-readable instructions further cause the at least one computing device to at least:

provide the modified command text to at least one second computing device;

receive from the at least one second computing device an indication of at least one acceptance of at least one modification of the modified command text;

generate a finalized command text based at least in part on the at least one acceptance and the modified command text; and

provide the finalized command text to at least one third computing device.

4 . The system of claim 3 , wherein the at least one second computing device comprises a voice assistant device, and the voice command is associated with the voice assistant device.

5 . The system of claim 3 , wherein the at least one third computing device comprises a voice skill service corresponding to an application associated with the voice command, and the command text is received from the voice skill service.

6 . The system of claim 1 , wherein the at least one lexical pattern corresponding to the user comprises a grammatical unit from the at least one electronic message, and the at least one lexical pattern corresponding to the user is determined based at least in part on a frequency that the grammatical unit occurs within the at least one electronic message.

7 . A method, comprising:

receiving command text corresponding to a voice command;

identifying at least one error in the command text, the error comprising one or more words, phrases or grammatical units that are determined to be erroneous;

determining at least one lexical pattern corresponding to a user associated with the voice command based at least in part on at least one electronic message associated with the user;

performing a comparison between the at least one error and the at least one lexical pattern corresponding to the user associated with the voice command;

generating modified command text based at least in part on the comparison between the at least one error and the at least one lexical pattern; and

determining that the modified command text does not comprise any error.

8 . The method of claim 7 , wherein generating the modified command text based at least in part on the comparison between the at least one error and the at least one lexical pattern further comprises substituting a grammatical unit corresponding to the at least one error for a grammatical unit corresponding to the at least one lexical pattern within the command text.

9 . The method of claim 7 , further comprising:

providing the modified command text to a voice assistant device;

receiving from the voice assistant device an indication of at least one acceptance of at least one modification of the modified command text;

generating a finalized command text based at least in part on the at least one acceptance and the modified command text; and

providing the finalized command text to at least one third computing device.

10 . The method of claim 9 , wherein the voice command is associated with the voice assistant device.

11 . The method of claim 9 , wherein the at least one third computing device comprises a voice skill service corresponding to an application associated with the voice command, and the command text is received from the voice skill service.

12 . The method of claim 7 , wherein the at least one lexical pattern corresponding to the user comprises a grammatical unit from the at least one electronic message, and the at least one lexical pattern corresponding to the user is determined based at least in part on a frequency that the grammatical unit occurs within the at least one electronic message.

13 . A non-transitory computer-readable medium comprising executable instructions, wherein the instructions, when executed by at least one processor, cause at least one computing device to at least:

receive command text corresponding to a voice command;

identify at least one error in the command text, the error comprising one or more words, phrases or grammatical units that are determined to be erroneous;

determine at least one lexical pattern corresponding to a user associated with the voice command based at least in part on at least one electronic message associated with the user;

perform a comparison between the at least one error and the at least one lexical pattern corresponding to the user associated with the voice command;

generate modified command text based at least in part on the comparison between the at least one error and the at least one lexical pattern; and

determine that the modified command text does not comprise any error.

14 . The non-transitory computer-readable medium of claim 13 , wherein the executable instructions that cause the at least one computing device to at least generate the modified command text based at least in part on the comparison between the at least one error and the at least one lexical pattern further cause the at least one computing device to at least substitute a grammatical unit corresponding to the at least one error for a grammatical unit corresponding to the at least one lexical pattern within the command text.

15 . The non-transitory computer-readable medium of claim 13 , wherein the at least one computing device is at least one first computing device, and the machine-readable instructions further cause the at least one computing device to at least:

provide the modified command text to at least one second computing device;

receive from the at least one second computing device an indication of at least one acceptance of at least one modification of the modified command text;

generate a finalized command text based at least in part on the at least one acceptance and the modified command text; and

provide the finalized command text to at least one third computing device.

16 . The non-transitory computer-readable medium of claim 15 , wherein

the at least one second computing device comprises a voice assistant device, and the voice command is associated with the voice assistant device, and

the at least one third computing device comprises a voice skill service corresponding to an application associated with the voice command, and the command text is received from the voice skill service.

17 . The non-transitory computer-readable medium of claim 13 , wherein the at least one lexical pattern corresponding to the user comprises a grammatical unit from the at least one electronic message, and the at least one lexical pattern corresponding to the user is determined based at least in part on a frequency that the grammatical unit occurs within the at least one electronic message.

Assignments (4)
PATENT ASSIGNMENT Recorded Aug 5, 2024
From: VMWARE LLC
To: OMNISSA, LLC
Reel/Frame 068327/0365 →
SECURITY INTEREST Recorded Jul 3, 2024
From: OMNISSA, LLC
To: UBS AG, STAMFORD BRANCH
Reel/Frame 068118/0004 →
CHANGE OF NAME Recorded Apr 25, 2024
From: VMWARE, INC.
To: VMWARE LLC
Reel/Frame 067239/0402 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 14, 2022
From: SHETTY, ROHIT PRADEEP
To: VMWARE, INC.
Reel/Frame 061424/0492 →
Priority Claims (1)
IN 202241041635 · Jul 20, 2022 · national
Continuity (1)
Related Publication 20240029729A1 · Jan 25, 2024
References Cited (12)
US 7826945B2 · Zhang · 2010 [cited by examiner]
US 8447602B2 · Bartosik · 2013 [cited by examiner]
US 11380304B1 · Ponnusamy · 2022 [cited by examiner]
US 20040002994A1 · Brill · 2004 [cited by examiner]
US 20060161434A1 · Faisman · 2006 [cited by examiner]
US 20070005206A1 · Zhang · 2007 [cited by examiner]
US 20070033026A1 · Bartosik · 2007 [cited by examiner]
US 20080167871A1 · Kim · 2008 [cited by examiner]
US 20150006170A1 · Caskey · 2015 [cited by examiner]
US 20150205779A1 · Bak · 2015 [cited by examiner]
US 20200020319A1 · Malhotra · 2020 [cited by examiner]
US 20220308718A1 · Klein · 2022 [cited by examiner]