Supporting multiple speech enabled user interface consoles within a motor vehicle

• US 20070038461A1
• Filed: 08/10/2005
• Published: 02/15/2007
• Est. Priority Date: 08/10/2005
• Status: Active Grant

• Current Assignee: Cerence Operating Company (Cerence Inc.)
• Original Assignee: International Business Machines Corporation
• Inventors: Abbott, Lisa, Florio, Michael, Woodward, Steven, Ruback, Harvey, Badt, Daniel, Eckhart, John, Hanson, Gary, Whitehead, William, Charoenruengkit, Werayuth
• Granted Patent: US 7,904,300 B2
• Time in Patent Office: Days
• US Class Current: 704/275
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications

Abstract

An in-vehicle system that shares speech processing resources among multiple applications located within a vehicle. The system can include one or more software applications, each associated with different functionally independent in-vehicle consoles. Each application can have a console specific user interface. The system can also include a single in-vehicle speech processing system implemented separately from the in-vehicle consoles. The speech processing system can execute speech processing tasks responsive to requests received from the applications. That is, the in-vehicle speech processing system can provide speech processing capabilities for the applications. The provided speech processing capabilities can include text-to-speech capabilities and speech recognition capabilities.

Claims

1. An in-vehicle system that shares speech processing resources among multiple applications located within a vehicle comprising:

a plurality of software applications, said applications associated with different ones of a plurality of functionally independent in-vehicle consoles, each having a console specific user interface; and

a single in-vehicle speech processing system implemented separately from said in-vehicle consoles are configured to execute speech processing tasks responsive to requests received from said applications, said in-vehicle speech processing system providing speech processing capabilities for said plurality of applications, said speech processing capabilities comprising at least one capability selected from a group consisting of a text-to-speech capability, a speech recognition capability, an enrollment capability, an acoustic baseform generation capability, and a speaker identification and verification capability.

2. The in-vehicle system of claim 1, wherein said in-vehicle consoles comprise at least two consoles selected from a group consisting of a vehicle navigation console, a vehicle video console, a vehicle electronic gaming console, a vehicle stereo console, a vehicle telephony console, a vehicle Web browsing console, a vehicle productivity application console, a vehicle radio console, a vehicle traffic information console, a vehicle commercial application console, and a vehicle interface console.

3. The in-vehicle system of claim 1, wherein at least two of said in-vehicle consoles are simultaneously and independently utilized by different in-vehicle users.

4. The in-vehicle system of claim 1, wherein said applications are developed using a software development kit (SDK) for an embedded software platform, wherein said speech processing capabilities for said applications use SDK provided libraries and Application Program Interfaces (APIs) to coordinate the usage of speech resources of the speech processing system among said applications.

5. The in-vehicle system of claim 1, wherein speech processing tasks are owned and managed by said speech processing system and not by any of said applications.

6. The in-vehicle system of claim 1, wherein interactions between said speech processing system and said applications are based upon a client/server model, where said speech processing system functions as a server that provides speech processing resources, and wherein each of said applications functions as a client that utilizes said provided speech processing resources.

7. The in-vehicle system of claim 6, wherein runtime interprocess communication (IPC) links are established between said speech processing system and said applications.

8. The in-vehicle system of claim 1, wherein said in-vehicle speech processing system is configured to simultaneously perform speech processing tasks for different ones of the software applications, the different software applications specifying that said speech processing tasks be performed in accordance with different languages.

9. The in-vehicle system of claim 1, wherein said speech processing tasks are provided to said software applications as server processes, each server process interfacing with an associated software application thorough a server process specific interface.

10. The in-vehicle system of claim 1, further comprising:

at least one camera configured to receive images of users located within a cabin of a vehicle in which said in-vehicle system is disposed;

at least one speech focus that establishes which of said applications are able to utilize resources of said speech processing system, wherein said images are used to determine which of said applications is to be granted said speech focus.

11. The in-vehicle system of claim 10, wherein said at least one speech focus comprises a text-to-speech speech focus and a speech recognition speech focus.

12. The in-vehicle system of claim 10, wherein said images are used to determine that a particular user has an intent to speak, wherein one of said in-vehicle consoles proximate to said determined user is responsively identified, wherein an application associated with said identified console is the application which is granted speech focus.

13. A method for multiple in-vehicle applications to share centrally provided speech processing resources comprising the steps of:

identifying a plurality of in-vehicle applications, each associated with an in-vehicle console, each application configured to be simultaneously and independently utilized by different users;

identifying a speech processing system for providing speech processing capabilities for said applications, said speech processing capabilities comprising text-to-speech capabilities and speech recognition capabilities;

receiving at least a first speech processing request from an in-vehicle console associated with a first of said in-vehicle applications;

receiving at least a second speech processing request from a second in-vehicle console associated with a second of said in-vehicle applications;

said speech processing system speech processing said first speech processing request to generate a first processing result;

said speech processing system speech recognizing said second speech processing request to generate a second processing result;

said first application performing a programmatic action based upon said first processing result; and

said second application performing a programmatic action based upon said second processing result.

14. The method of claim 13, wherein said first speech processing request and said second speech processing request comprise speech utterances, and wherein said first processing result and said second processing result are speech recognition results generated by the speech processing system based upon said speech utterances.

15. The method of claim 13, wherein said first speech processing request and said second speech processing request comprise text input, and wherein said first processing result and said second processing result comprise speech which has been generated by the speech processing system based upon said text input.

16. The method of claim 13, wherein said first speech processing request and second speech processing request are request received from different in-vehicle consoles responsive to actions taken by different users, wherein said speech processing system receives said first speech processing request and second speech processing request at approximately the same time and wherein the speech processing system is unable to simultaneously process said first speech processing request and said second speech processing request, wherein said speech processing system determines an order in which the first speech processing request and the second speech processing request are to be processed based upon which of the first application and the second application has speech focus.

17. The method of claim 16, further comprising:

receiving images of users located within a cabin of a vehicle;

determining which of said first and second applications has speech focus based at least in part upon said images.

18. A method for multiple in-vehicle applications to share centrally provided speech processing resources comprising the steps of:

identifying a plurality of in-vehicle applications, each associated with an in-vehicle console, each application configured to be simultaneously and independently utilized by different users, wherein each of said applications are developed using a software development kit (SDK) for an embedded software platform;

identifying a speech processing system for providing speech processing capabilities for said applications, said speech processing capabilities comprising at least one capability selected from a group consisting of a text-to-speech capability, a speech recognition capability, an enrollment capability, an acoustic baseform generation capability, and a speaker identification and verification capability; and

digitally exchanging information between said speech processing system and said applications based upon a client/server model.

19. The method of claim 18, further comprising the steps of:

said in-vehicle applications competing for speech focus, wherein speech focus determines which of said competing applications has priority over other competing applications for utilizing speech resources provided by the speech processing system.

20. The method of claim 19, further comprising the steps of:

receiving images of users located within a cabin of a vehicle; and

determining which of said in-vehicle applications has speech focus based at least in part upon said images.