Managing in vehicle speech interfaces to computer-based cloud services due recognized speech, based on context

Patent metadata

Field	Value
Publication number	US-9679562-B2
Application number	US-201213604763-A
Country	US
Kind code	B2
Filing date	Sep 6, 2012
Priority date	Sep 6, 2012
Publication date	Jun 13, 2017
Grant date	Jun 13, 2017

Abstract

A method of managing speech interfaces to computer-based services includes beginning a first speech session that is carried out in a vehicle over a short-range wireless connection between a vehicle occupant and a mobile device; detecting an initiation of a second speech session while the first speech session is being carried out; determining an assigned priority level of the first speech session relative to an assigned priority level of the second speech session based on a first speech context identified in the first speech session and a second speech context identified in the second speech session; and when the assigned priority level of the second speech session has a higher priority than the assigned priority level of the first speech session, carrying out a session-appropriate action on the first speech session.

First claim

The invention claimed is:

1. A method of managing speech interfaces to computer-based services, the method comprising:
(a) beginning a first speech session that is carried out in a vehicle between a vehicle occupant and a mobile device;
(b) detecting an initiation of a second speech session between the vehicle occupant and the mobile device while the first speech session is being carried out, wherein each of the first and second speech sessions comprise:
receiving and recognizing a speech input from the vehicle occupant;
obtaining a service result from a cloud service that is responsive to the content of the speech input; and
providing the service result to the vehicle occupant;

(c) determining an assigned priority level of the first speech session relative to an assigned priority level of the second speech session based on a first speech context identified in the first speech session and a second speech context identified in the second speech session from speech recognition results; and
(d) when the assigned priority level of the second speech session has a higher priority than the assigned priority level of the first speech session, carrying out a session-appropriate action on the first speech session.

2. The method of claim 1 , further comprising a step of receiving a priority level ranking for the first speech session and the second speech session from the vehicle occupant.

3. The method of claim 2 , further comprising a step of storing the received priority level ranking at the mobile device.

4. The method of claim 1 , further comprising a step of pausing the first speech session until the second speech session is complete.

5. The method of claim 4 , further comprising a step of returning to the first speech session after the second speech session is complete.

6. The method of claim 1 , further comprising a step of sending at least a portion of the first speech session to a cloud speech service.

7. A method of managing speech interfaces to computer-based services, the method comprising:
(a) receiving one or more priority level rankings at a mobile device from a user;
(b) associating each of the priority level rankings with a speech context or a desired service accessible by the mobile device;
(c) beginning a first speech session at a vehicle using an audio user interface installed on the vehicle and wirelessly linked to the mobile device;
(d) detecting an initiation of a second speech session at the mobile device, wherein each of the first and second speech sessions comprise:
receiving and recognizing a speech input from the user;
obtaining a service result from a cloud service that is responsive to the content of the speech input; and
providing the service result to the user;

(e) identifying the priority level ranking of the first speech session and the priority level ranking of the second speech session based on the associated priority level rankings and on a first speech context identified in the first speech session and a second speech context identified in the second speech session from speech recognition results; and
(f) carrying out a session-appropriate action for the first speech session or the second speech session based on a comparison of the identified priority level rankings of the first speech session and the second speech session.

8. The method of claim 7 , wherein the session-appropriate action further comprises placing the first speech session or the second speech session in a paused state based on which of the first speech session and the second speech session has a lower identified priority level ranking.

9. The method of claim 8 , further comprising a step of ending the paused state.

10. The method of claim 7 , further comprising a step of sending at least a portion of the first speech session to a cloud speech service.

11. The method of claim 7 , further comprising a step of storing the received priority level rankings at the mobile device.

Assignees

• Burke Denis R
• Gurovich Danilo
• Rudman Daniel E
• Fry Keith A
• Mccutchen Shane M
• Carnevale Marco T
• Gupta Mukesh
• Gm Global Tech Operations Llc

Inventors

• Burke Denis R
• Gurovich Danilo
• Rudman Daniel E
• Fry Keith A
• Mccutchen Shane M
• Carnevale Marco T
• Gupta Mukesh

Classifications

• G10L15/26

  Speech to text systems (G10L15/08 takes precedence) · CPC title

• B60R16/0373

  Voice control (in general G10L) · CPC title

• H04B1/082

  to be used in vehicles (H04B1/086 takes precedence; holding or mounting accessories B60R11/02) · CPC title

• G10L15/34

  Adaptation of a single recogniser for parallel processing, e.g. by use of multiple processors or cloud computing · CPC title

• G10L15/265

  Physics · mapped topic