IP Library › Granted Patent US 12,598,256
Granted Patent B2
US 12,598,256 · App. 17/843,731 · Granted Apr 7, 2026

Disrupted-speech management engine for a meeting management system

Inventor: Mrinal Kumar Sharma (Redmond, WA)
Assignee: Microsoft Technology Licensing, LLC
H04M3/563G06V40/168G10L15/02G10L15/063G10L15/22G10L25/57H04L65/403H04L65/80G10L2015/025H04M2201/405
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 12,598,256
App. No.
17/843,731
Granted
Apr 7, 2026
Kind
B2
Abstract

Methods, systems, and computer storage media for providing a disrupted-speech assistance service associated with a disrupted-speech management engine of a meeting management system. The disrupted-speech assistance service is an accessibility service that supports accessibility operations of a disrupted-speech management engine to provide disrupted-speech assistance features in a meeting management system. In operation, meeting data comprising audio data is accessed. The audio data is analyzed to determine that the audio data comprises disrupted-speech at a threshold level of disrupted-speech. Based on the audio data comprising disrupted-speech at the threshold level of disrupted-speech, one or more disrupted-speech assistance operations for a meeting can be executed. The one or more disrupted-speech assistance operations comprises identifying a disrupted-speech word; determining an alternative word for the disrupted-speech word. A disrupted-speech assistance interface is generated based on the one or more disrupted-speech assistance operations. The disrupted-speech assistance interface comprises the alternative word for the disrupted-speech word.

Claims (68)

1 . A computerized system, the computerized system comprising:

at least one computer processor; and computer memory storing computer-useable instructions that, when used by the at least one computer processor, cause the at least one computer processor to perform operations comprising:

accessing, at a disrupted-speech management engine, meeting data of a meeting associated with a user, the meeting data comprising audio data and video data, wherein the meeting data is associated with a meeting management system for videoconferencing,

wherein a disrupted-speech machine learning engine supports training one or more machine learning models based on a disrupted-speech machine learning training dataset comprising a disrupted-speech dataset associated with historical and contextual data of meetings,

wherein the one or more machine learning models are utilized in performing disrupted-speech assistance operations,

wherein the meeting management system and the one or more machine learning models support a disrupted-speech assistance service that is integrated into the meeting management system via the disrupted-speech management engine;

determining that the audio data comprises disrupted-speech at a threshold level of disrupted-speech;

based on the audio data comprising disrupted-speech at the threshold level of disrupted-speech, execute one or more disrupted-speech assistance operations for the meeting, wherein the one or more disrupted-speech assistance operations comprises:

identifying a disrupted-speech word based on the audio data; and;

determining an alternative word for the disrupted-speech word; and causing generation of a disrupted-speech assistance interface based on the one or more disrupted-speech assistance operations, wherein the disrupted-speech assistance interface comprises the alternative word for the disrupted-speech word, wherein the disrupted-speech assistance interface supports generating an indication of user encouragement when a determination is made that user has overcome an instance of disrupted-speech, wherein the disrupted-speech assistance interface includes each of: a digital assistant interface comprising the disrupted-speech word and the alternative word; an indication to attendees of the meeting that the user is experiencing disrupted-speech; an indication of user encouragement; and a disrupted-speech timeline comprising one or more instances of disrupted speech, wherein an instance of disrupted speech is associated with a timestamp and a count of a number times the disrupted-speech word was repeated.

2 . The computerized system of claim 1 , wherein the user is associated with a disrupted-speech user profile of the disrupted-speech assistance service.

3 . The computerized system of claim 2 wherein the disrupted-speech user profile comprises the disrupted-speech dataset that is stored and utilized in performing the one or more disrupted-speech assistance operations.

4 . The computerized system of claim 1 , wherein determining that the audio data comprises disrupted-speech at the threshold level of disrupted speech is based on determining an occurrence frequency of consecutive phonemes within a predefined period of time.

5 . The computerized system of claim 4 , wherein determining that the audio data comprises disrupted-speech is further based on the video data of the meeting data, wherein the video data is analyzed for facial features associated with disrupted-speech to support determining that the audio data comprises disrupted-speech.

6 . The computerized system of claim 1 , wherein the disrupted-speech assistance interface supports communicating a disrupted-speech recovery reward based on audio data associated with the user and the alternative word, wherein the disrupted-speech recovery reward is generated based on the determination that the user has overcome the instance of disrupted-speech.

7 . The computerized system of claim 1 , wherein the one or more disrupted-speech assistance operations include each of:

initializing a digital assistant associated with generating the disrupted-speech assistance interface;

communicating an indication to attendees of the meeting that the user is experiencing disrupted-speech;

scanning one or more slides of a slide deck associated with the meeting to identify the disrupted-speech word;

personalizing the alternative word for the disrupted-speech word based on the disrupted-speech dataset associated with a disrupted-speech user profile of the user;

communicating the indication of user encouragement; and

communicating a disrupted-speech recovery reward based on audio data associated with the user and the alternative word.

8 . One or more computer-storage media having computer-executable instructions embodied thereon that, when executed by a computing system having a processor and memory, cause the processor to:

communicate, from a client device, meeting data of a meeting associated with a user, the meeting data comprising audio data and video data, wherein the meeting data is associated with a meeting management system for videoconferencing,

wherein a disrupted-speech machine learning engine supports training one or more machine learning models based on a disrupted-speech machine learning training dataset comprising a disrupted-speech dataset associated with historical and contextual data of meetings,

wherein the one or more machine learning models are utilized in performing disrupted-speech assistance operations,

wherein the meeting management system and the one or more machine learning models support a disrupted-speech assistance service that is integrated into the meeting management system via a disrupted-speech management engine;

based on communicating the meeting data, receive a disrupted-speech word based on the audio data and an alternative word for the disrupted-speech word, wherein disrupted-speech word and the alternative word for the disrupted-speech word are associated with one or more disrupted-speech assistance operations of the disrupted-speech management engine; and

cause presentation of a disrupted-speech assistance interface based on the one or more disrupted-speech assistance operations, wherein the disrupted-speech assistance interface comprises the alternative word for the disrupted-speech word, wherein the disrupted-speech assistance interface supports generating an indication of user encouragement when a determination is made that user has overcome an instance of disrupted-speech, wherein the disrupted-speech assistance interface includes each of: a digital assistant interface comprising the disrupted-speech word and the alternative word; an indication to attendees of the meeting that the user is experiencing disrupted-speech; an indication of user encouragement; and a disrupted-speech timeline comprising one or more instances of disrupted speech, wherein an instance of disrupted speech is associated with a timestamp and a count of a number times the disrupted-speech word was repeated.

9 . The one computer-storage media of claim 8 , wherein the user is associated with a disrupted-speech user profile of the disrupted-speech assistance service.

10 . The one computer-storage media of claim 9 , wherein the disrupted-speech user profile comprises the disrupted-speech dataset that is stored and utilized in performing the one or more disrupted-speech assistance operations.

11 . The one computer-storage media of claim 8 , wherein the disrupted-speech assistance interface supports communicating a disrupted-speech recovery reward based on audio data associated with the user and the alternative word, wherein the disrupted-speech recovery reward is generated based on the determination that the user has overcome the instance of disrupted-speech.

12 . The one computer-storage media of claim 11 , wherein the one or more disrupted-speech assistance operations include each of:

initializing a digital assistant associated with generating the disrupted-speech assistance interface;

communicating an indication to attendees of the meeting that the user is experiencing disrupted-speech;

scanning one or more slides of a slide deck associated with the meeting to identify the disrupted-speech word;

personalizing the alternative word for the disrupted-speech word based on the disrupted-speech dataset associated with a disrupted-speech user profile of the user;

communicating the indication of user encouragement; and

communicating a disrupted-speech recovery reward based on audio data associated with the user and the alternative word.

13 . The one computer-storage media of claim 8 , wherein the disrupted-speech assistance interface includes each of:

a digital assistant interface comprising the disrupted-speech word and the alternative word;

an indication to attendees of the meeting that the user is experiencing disrupted-speech,

the indication of user encouragement; and

a disrupted-speech timeline comprising one or more instances of disrupted speech, wherein an instance of disrupted speech is associated with a timestamp and a count of a number times the disrupted-speech word was repeated.

14 . A computer-implemented method, comprising:

accessing, at a disrupted-speech management engine, meeting data of a meeting associated with a user, the meeting data comprising audio data and video data, wherein the meeting data is associated with a meeting management system for videoconferencing,

wherein a disrupted-speech machine learning engine supports training one or more machine learning models based on a disrupted-speech machine learning training dataset comprising a disrupted-speech dataset associated with historical and contextual data of meetings,

wherein the one or more machine learning models are utilized in performing disrupted-speech assistance operations,

wherein the meeting management system and the one or more machine learning model support a disrupted-speech assistance service that is integrated into the meeting management system via the disrupted-speech management engine;

determining that the audio data comprises disrupted-speech at a threshold level of disrupted-speech;

based on the audio data comprising disrupted-speech at the threshold level of disrupted-speech, execute one or more disrupted-speech assistance operations for the meeting, wherein the one or more disrupted-speech assistance operations comprises:

identifying a disrupted-speech word based on the audio data; and;

determining an alternative word for the disrupted-speech word; and causing generation of a disrupted-speech assistance interface based on the one or more disrupted-speech assistance operations, wherein the disrupted-speech assistance interface comprises the alternative word for the disrupted-speech word, wherein the disrupted-speech assistance interface supports generating an indication of user encouragement when a determination is made that user has overcome an instance of disrupted-speech, wherein the disrupted-speech assistance interface includes each of: a digital assistant interface comprising the disrupted-speech word and the alternative word; an indication to attendees of the meeting that the user is experiencing disrupted-speech; an indication of user encouragement; and a disrupted-speech timeline comprising one or more instances of disrupted speech, wherein an instance of disrupted speech is associated with a timestamp and a count of a number times the disrupted-speech word was repeated.

15 . The computer-implemented method of claim 14 , wherein determining that the audio data comprises disrupted-speech at the threshold level of disrupted speech is based on determining an occurrence frequency of consecutive phonemes within a predefined period of time.

16 . The computer-implemented method of claim 15 , wherein determining that the audio data comprises disrupted-speech is further based on the video data of the meeting data, wherein the video data is analyzed for facial features associated with disrupted-speech to support determining that the audio data comprises disrupted-speech.

17 . The computer-implemented method of claim 14 , wherein the disrupted-speech assistance interface supports communicating a disrupted-speech recovery reward based on audio data associated with the user and the alternative word, wherein the disrupted-speech recovery reward is generated based on the determination that the user has overcome the instance of disrupted-speech.

18 . The computer-implemented method of claim 14 , wherein the one or more disrupted-speech assistance operations further each:

initializing a digital assistant associated with generating the disrupted-speech assistance interface;

communicating an indication to attendees of the meeting that the user is experiencing disrupted-speech;

scanning one or more slides of a slide deck associated with the meeting to identify the disrupted-speech word;

personalizing the alternative word for the disrupted-speech word based on the disrupted-speech dataset associated with a disrupted-speech user profile of the user;

communicating the indication of user encouragement; and

communicating a disrupted-speech recovery reward based on audio data associated with the user and the alternative word.

19 . The computer-implemented method of claim 14 , wherein the disrupted-speech assistance interface further comprises each of:

a digital assistant interface comprising the disrupted-speech word and the alternative word;

an indication to attendees of the meeting that the user is experiencing disrupted-speech;

the indication of user encouragement; and

a disrupted-speech timeline comprising one or more instances of disrupted speech, wherein an instance of disrupted speech is associated with a timestamp and a count of a number times the disrupted-speech word was repeated.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 30, 2022
From: SHARMA, MRINAL KUMAR
To: MICROSOFT TECHNOLOGY LICENSING, LLC
Reel/Frame 061357/0189 →
Continuity (1)
Related Publication 20230412734A1 · Dec 21, 2023
References Cited (16)
US 9826929B2 · Steinberg-Shapira et al. · 2017 [cited by applicant]
US 10524715B2 · Sahin · 2020 [cited by examiner]
US 10770069B2 · Mithra et al. · 2020 [cited by applicant]
US 11024297B2 · Aravamudan et al. · 2021 [cited by applicant]
US 11594149B1 · Edalat · 2023 [cited by examiner]
US 20190043490A1 · Rivlin · 2019 [cited by examiner]
US 20190087870A1 · Gardyne · 2019 [cited by examiner]
US 20190311732A1 · Vadassery · 2019 [cited by examiner]
US 20200090809A1 · Baughman · 2020 [cited by examiner]
US 20210065582A1 · Liao et al. · 2021 [cited by applicant]
US 20210315516A1 · Rattehalli et al. · 2021 [cited by applicant]
Das, et al., “Stuttering Speech Disfluency Prediction using Explainable Attribution Vectors of Facial Muscle Movements”, In Repository of arXiv:2010.01231v1, Oct. 2, 2020, pp. 1-10. [cited by applicant]
Sheikh, et al., “Machine Learning for Stuttering Identification: Review, Challenges & Future Directions”, In Repository of arXiv:2107.04057v2, Jul. 12, 2021, pp. 1-27. [cited by applicant]
Xu, Ronald, “A Stuttering Degree Diagnosis Tool Based on a Neural Network Model Trained with Multimodal Data”, In Journal of Editorial Board, Dec. 13, 2020, 4 Pages. [cited by applicant]
Ghai, et al., “Fluent: An AI Augmented Writing Tool for People who Stutter”, In Proceedings of the 23rd International ACM SIGACCESS Conference on Computers and Accessibility, Oct. 18, 2021, 8 Pages. [cited by applicant]
“International Search Report and Written Opinion Issued in PCT Application No. PCT/US23/019692”, Mailed Date: Aug. 2, 2023, 14 Pages. [cited by applicant]