IP Library › Granted Patent US 11,227,588
Granted Patent B2
US 11,227,588 · App. 16/213,194 · Granted Jan 18, 2022

System and method for feature based beam steering

Inventors: Tobias Wolff (Neu-Ulm Burlafingen, DE); Simon Graf (Ulm, DE)
Assignee: NUANCE COMMUNICATIONS, INC.
G10L15/22G10L15/02G10L15/30G10L25/21
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 11,227,588
App. No.
16/213,194
Granted
Jan 18, 2022
Kind
B2
Abstract

A method, computer program product, and computer system for identifying, by a computing device, a plurality of sources. One or more feature values of a plurality of features may be assigned to a first source of the plurality of sources. One or more feature values of the plurality of features may be assigned to a second source of the plurality of sources. A first score for the first source and a second score for the second source may be determined based upon, at least in part, the one or more feature values assigned to the first source and the second source. One of the first source and the second source may be selected for spatial processing based upon, at least in part, the first score for the first source and the second score for the second source.

Claims (30)

1. A computer-implemented method comprising:

identifying, by a computing device, a plurality of sources;

assigning one or more feature values of a plurality of features to a first source of the plurality of sources, wherein each of the one or more feature values assigned to the first source is assigned from a predetermined set of values that each respectively indicate at least one feature type of the plurality of features exhibited by the first source, wherein the at least one feature type of the plurality of features exhibited by the first source and assigned one of the one or more values includes source energy of the first source when compared to any other source of the plurality of sources;

assigning one or more feature values of the plurality of features to a second source of the plurality of sources, wherein each of the one or more feature values assigned to the second source is assigned from the predetermined set of values that each respectively indicate at least one feature type of the plurality of features exhibited by the second source, wherein the at least one feature type of the plurality of features exhibited by the second source and assigned one of the one or more values includes source energy of the second source when compared to any other source of the plurality of sources;

determining a first score for the first source and a second score for the second source based upon, at least in part, the one or more feature values assigned to the first source and the second source from the predetermined set of values, wherein determining the first score for the first source and the second score for the second source includes assigning weights to the one or more feature values, wherein the weights assigned to the one or more feature values are dynamically assigned based upon the plurality of features assigned; and

selecting one of the first source and the second source for spatial processing based upon, at least in part, the first score for the first source and the second score for the second source.

2. The computer-implemented method of claim 1 wherein the at least one feature type of the plurality of features further includes one of source starting and stopping activity.

3. The computer-implemented method of claim 1 wherein the at least one feature type of the plurality of features further includes source mobility.

4. The computer-implemented method of claim 1 wherein the at least one feature type of the plurality of features further includes one of source persistency of activity and source activity.

5. The computer-implemented method of claim 1 wherein identifying the plurality of sources includes at least one of multisource localization and video.

6. A computer program product residing on a non-transitory computer readable storage medium having a plurality of instructions stored thereon which, when executed across one or more processors, causes at least a portion of the one or more processors to perform operations comprising:

identifying a plurality of sources;

assigning one or more feature values of a plurality of features to a first source of the plurality of sources, wherein each of the one or more feature values assigned to the first source is assigned from a predetermined set of values that each respectively indicate at least one feature type of the plurality of features exhibited by the first source, wherein the at least one feature type of the plurality of features exhibited by the first source and assigned one of the one or more values includes source energy of the first source when compared to any other source of the plurality of sources;

assigning one or more feature values of the plurality of features to a second source of the plurality of sources, wherein each of the one or more feature values assigned to the second source is assigned from the predetermined set of values that each respectively indicate at least one feature type of the plurality of features exhibited by the second source, wherein the at least one feature type of the plurality of features exhibited by the second source and assigned one of the one or more values includes source energy of the second source when compared to any other source of the plurality of sources;

determining a first score for the first source and a second score for the second source based upon, at least in part, the one or more feature values assigned to the first source and the second source from the predetermined set of values, wherein determining the first score for the first source and the second score for the second source includes assigning weights to the one or more feature values, wherein the weights assigned to the one or more feature values are dynamically assigned based upon the plurality of features assigned; and

selecting one of the first source and the second source for spatial processing based upon, at least in part, the first score for the first source and the second score for the second source.

7. The computer program product of claim 6 wherein the at least one feature type of the plurality of features further includes one of source starting and stopping activity.

8. The computer program product of claim 6 wherein the at least one feature type of the plurality of features further includes source mobility.

9. The computer program product of claim 6 wherein the at least one feature type of the plurality of features further includes one of source persistency of activity and source activity.

10. The computer program product of claim 6 wherein identifying the plurality of sources includes at least one of multisource localization and video.

11. A computing system including one or more processors and one or more memories configured to perform operations comprising:

identifying a plurality of sources;

assigning one or more feature values of a plurality of features to a first source of the plurality of sources, wherein each of the one or more feature values assigned to the first source is assigned from a predetermined set of values that each respectively indicate at least one feature type of the plurality of features exhibited by the first source, wherein the at least one feature type of the plurality of features exhibited by the first source and assigned one of the one or more values includes source energy of the first source when compared to any other source of the plurality of sources;

assigning one or more feature values of the plurality of features to a second source of the plurality of sources, wherein each of the one or more feature values assigned to the second source is assigned from the predetermined set of values that each respectively indicate at least one feature type of the plurality of features exhibited by the second source, wherein the at least one feature type of the plurality of features exhibited by the second source and assigned one of the one or more values includes source energy of the second source when compared to any other source of the plurality of sources;

determining a first score for the first source and a second score for the second source based upon, at least in part, the one or more feature values assigned to the first source and the second source from the predetermined set of values, wherein determining the first score for the first source and the second score for the second source includes assigning weights to the one or more feature values, wherein the weights assigned to the one or more feature values are dynamically assigned based upon the plurality of features assigned; and

selecting one of the first source and the second source for spatial processing based upon, at least in part, the first score for the first source and the second score for the second source.

12. The computing system of claim 11 wherein the at least one feature type of the plurality of features further includes one of source starting and stopping activity.

13. The computing system of claim 11 wherein the at least one feature type of the plurality of features further includes source mobility.

14. The computing system of claim 11 wherein the at least one feature type of the plurality of features further includes one of source persistency of activity and source activity.

15. The computing system of claim 11 wherein identifying the plurality of sources includes at least one of multisource localization and video.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 14, 2023
From: NUANCE COMMUNICATIONS, INC.
To: MICROSOFT TECHNOLOGY LICENSING, LLC
Reel/Frame 065578/0676 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 14, 2019
From: WOLFF, TOBIAS; GRAF, SIMON
To: NUANCE COMMUNICATIONS, INC.
Reel/Frame 048334/0887 →