Voice focus enabled by predetermined triggers

• US 9,508,343 B2
• Filed: 05/27/2014
• Issued: 11/29/2016
• Est. Priority Date: 05/27/2014
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Bush, Hobert III, Fox, James E., Shergill, Vishavpal S., Smith, Justin P.
• Primary Examiner(s): ADESANYA, OLUJIMI A
• Application Number:
  US14/288,114
• Publication Number:
  US 20150348553A1
• Time in Patent Office: 917 Days
• Field of Search: 704/226, 704/233, 704/235, 704/246
• US Class Current: 1/1
• CPC Class Codes: G10L 15/08 Speech classification or search
• CPC Class Codes: G10L 15/20 Speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech G10L21/02 takes precedence
• CPC Class Codes: G10L 17/00 Speaker identification or verification techniques
• CPC Class Codes: G10L 2021/02087 the noise being separate speech, e.g. cocktail party
• CPC Class Codes: G10L 21/0208 Noise filtering

Abstract

Provided are techniques for voice focus enabled by predetermined triggers. Voice recognition is used to identify one or more pre-determined triggers from a voice of a speaker. In response to identifying the one or more pre-determined triggers, a voice recognition template is dynamically created for the voice of the speaker, and the voice recognition template and voice isolation are used to focus on the voice from the speaker.

Claims

1. A computer system, comprising:

one or more processors, one or more computer-readable memories and one or more computer-readable, tangible storage devices; and

program instructions, stored on at least one of the one or more computer-readable, tangible storage devices for execution by at least one of the one or more processors via at least one of the one or more memories, to perform operations comprising;

using voice recognition to identify one or more pre-determined triggers from each voice of multiple speakers addressing a listener nearly simultaneously; and

in response to identifying the one or more pre-determined triggers,

for each of the multiple speakers that does not have a previously stored voice recognition template, dynamically creating a voice recognition template to store voice biometrics of that speaker;

for each of the multiple speakers that does have a stored voice recognition template, updating the voice recognition template;

selecting a speaker from among the multiple speakers to focus on based on clarity of that speaker, direction of that speaker, one or more keywords spoken by that speaker, and whether there is a previously stored voice recognition template for that speaker; and

using the voice recognition template and voice isolation to focus on the voice from the selected speaker.

2. The computer system of claim 1, wherein the one or more pre-determined triggers include one or more words that address a listener.

3. The computer system of claim 1, wherein focusing on the voice includes cancelling out background noise.

4. The computer system of claim 1, wherein focusing on the voice includes isolating words from the speaker.

5. The computer system of claim 1, wherein the operations further comprise:

determining that the voice recognition template exists for the speaker.

6. The computer system of claim 1, wherein using the voice recognition template and the voice isolation to focus on the voice from the selected speaker is performed in a hearing device.

7. The computer system of claim 1, wherein a Software as a Service (SaaS) is configured to perform system operations.

8. A computer program product, the computer program product comprising a computer readable storage medium having program code embodied therewith, the program code executable by at least one processor to perform:

using, by the at least one processor, voice recognition to identify one or more pre-determined triggers from each voice of multiple speakers addressing a listener nearly simultaneously; and

in response to identifying the one or more pre-determined triggers,

for each of the multiple speakers that does not have a previously stored voice recognition template, dynamically creating, by the at least one processor, a voice recognition template to store voice biometrics of that speaker;

for each of the multiple speakers that does have a stored voice recognition template, updating the voice recognition template;

selecting a speaker from among the multiple speakers to focus on based on clarity of that speaker, direction of that speaker, one or more keywords spoken by that speaker, and whether there is a previously stored voice recognition template for that speaker; and

using, by the at least one processor, the voice recognition template and voice isolation to focus on the voice from the selected speaker.

9. The computer program product of claim 8, wherein the one or more pre-determined triggers include one or more words that address a listener.

10. The computer program product of claim 8, wherein focusing on the voice includes cancelling out background noise.

11. The computer program product of claim 8, wherein focusing on the voice includes isolating words from the speaker.

12. The computer program product of claim 8, wherein the program code is executable by the at least one processor to perform:

determining, by the at least one processor, that the voice recognition template exists for the speaker.

13. The computer program product of claim 8, wherein a Software as a Service (SaaS) is configured to perform computer program product operations.

14. The computer program product of claim 8, using the voice recognition template and the voice isolation to focus on the voice from the selected speaker is performed in a hearing device.