Systems and methods for dynamic download of embedded voice components

• US 9,997,160 B2
• Filed: 07/01/2013
• Issued: 06/12/2018
• Est. Priority Date: 07/01/2013
• Status: Active Grant

• Current Assignee: Toyota Jidosha Kabushiki Kaisha (Toyota Motor Corporation)
• Original Assignee: Toyota Motor Engineering & Manufacturing North America Incorporated (Toyota Motor Corporation)
• Inventors: Schmidt, Eric Randell
• Primary Examiner(s): Lerner, Martin
• Application Number:
  US13/932,241
• Publication Number:
  US 20150006182A1
• Time in Patent Office: 1,807 Days
• Field of Search: 704231, 704243, 704244, 704251, 704255, 704270, 7042701, 704275
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 2015/228 of application context

Abstract

Systems and methods for dynamic download of embedded voice components are disclosed. One embodiment may be configured to receive an application via a wireless communication, where the application comprises a speech recognition component, receive the voice command from a user, and analyze the speech recognition component to determine a translation action to perform, based on the voice command. In some embodiments, in response to determining that the translation action includes downloading a vocabulary from a first remote computing device, the vocabulary may be downloaded from the first remote computing device to utilize the vocabulary to translate the voice command. In some embodiments, in response to determining that the translation action includes communicating the voice command to a second remote computing device, the voice command may be sent to the second remote computing device and receive a translated version of the voice command.

Claims

1. A method for dynamic download of embedded voice components comprising:

downloading an application, wherein the application comprises a speech recognition component that includes a speech recognition instruction;

installing the application, wherein installing the application comprises determining whether the speech recognition component includes a launch instruction and, in response to determining that the speech recognition component includes the launch instruction, installing the launch instruction into an embedded speech recognition application;

receiving a voice command from a user to implement the function;

identifying an intent and a criteria from the voice command, wherein the intent relates to an action to be taken and wherein the criteria indicates an item to which the action is directed;

determining whether the speech recognition component comprises a first vocabulary and, in response to determining that the speech recognition component comprises the first vocabulary, determine whether the first vocabulary recognizes the criteria and the intent;

in response to determining that the criteria is not recognized by the first vocabulary, performing an internet search to determine the criteria;

in response to determining that the intent is recognized by the first vocabulary, utilizing the first vocabulary to recognize the intent; and

in response to determining that the intent is not recognized by the first vocabulary, determining whether the speech recognition component indicates that a second vocabulary from a different application will be utilized to recognize the intent, and utilizing the different application to translate the intent.

2. The method of claim 1, further comprising:

determining whether the speech recognition component indicates that the voice command will be sent to a remote computing device; and

in response to determining that the speech recognition component indicates that the voice command will be sent to the remote computing device for translation, sending the voice command to the remote computing device, receiving the translated command, and performing the functional action that fulfills the voice command.

3. The method of claim 1, further comprising performing the functional action that fulfills the voice command.

4. The method of claim 1, further comprising:

receiving an audible user launch command from the user;

determining whether the audible user launch command corresponds with a stored launch command for launching the application; and

in response to determining that the audible user launch command corresponds with the stored launch command for launching the application, launching the application.

5. The method of claim 1, wherein the speech recognition component comprises a stored launch command for launching the application via an audible user launch command.

6. The method of claim 5, further comprising:

loading the stored launch command;

receiving the audible user launch command to launch the application;

determining whether the audible user launch command relates to the application; and

launching the application, based on the audible user launch command.

7. The method of claim 5, further comprising providing a user option to define the stored launch command.

8. A system for dynamic download of embedded voice components comprising:

a microphone for receiving a voice command;

a processor for executing logic; and

a memory component that stores logic that, when executed by the processor, causes the processor to perform at least the following;

receive an application via a wireless communication, wherein the application comprises a speech recognition component;

receive, via the microphone, the voice command from a user;

identify a criteria and an intent from the voice command;

analyze the speech recognition component to determine a translation action to perform, based on the voice command;

in response to determining that the translation action includes downloading a vocabulary from a first remote computing device, download the vocabulary from the first remote computing device and utilize the vocabulary to recognize the criteria and the intent;

in response to determining that the vocabulary does not recognize the criteria, perform an internet search to determine the criteria;

in response to determining that the vocabulary does not recognize the intent, send the voice command to the second remote computing device and receive a translated version of the intent.

9. The system of claim 8, wherein the logic further causes the processor to perform a functional action that fulfills the voice command.

10. The system of claim 8, wherein the logic further causes the processor to perform at least the following:

receive an audible user launch command from the user;

determine whether the audible user launch command corresponds with a stored launch command for launching the application; and

in response to determining that the audible user launch command corresponds with the stored launch command for launching the application, launch the application.

11. The system of claim 8, wherein the speech recognition component comprises a stored launch command for launching the application via the voice command.

12. The system of claim 11, wherein the logic further causes the processor to perform at least the following:

load the stored launch command;

receive an audible user launch command to launch the application;

determine whether the audible user launch command relates to the application; and

launch the application, based on the audible user launch command.

13. The system of claim 8, wherein the logic further causes the processor to provide a user option to define a stored launch command.

14. A vehicle speech recognition system for dynamic download of embedded voice components comprising:

a processor; and

a memory component that stores logic that, when executed by the processor, causes the processor to perform at least the following;

install an application, wherein the application comprises a speech recognition component that includes a speech recognition instruction;

receive a voice command from a user;

identify an intent and a criteria from the voice command;

determine whether the speech recognition component comprises a first vocabulary and, in response to determining that the speech recognition component comprises the first vocabulary, utilize the first vocabulary to recognize the criteria and the intent;

in response to determining that the criteria is not recognized by first vocabulary, perform an internet search to determine the criteria; and

determine whether the first vocabulary recognizes the intent and, in response to determining that the first vocabulary does not recognize the intent, send the voice command to the remote computing device, receive the translated intent, and perform the functional action that fulfills the voice command.

15. The vehicle speech recognition system of claim 14, wherein installing the application further comprises determining whether the speech recognition component includes a stored launch command and, in response to determining that the speech recognition component includes the stored launch command, install the stored launch command into an embedded speech recognition application.

16. The vehicle speech recognition system of claim 15, wherein the logic further causes the processor to perform at least the following:

receive an audible user launch command from the user;

determine whether the user launch command corresponds with the stored launch command; and

in response to determining that the audible user launch command corresponds with the stored launch command, launch the application.

17. The vehicle speech recognition system of claim 14, wherein the logic further causes the processor to determine whether the speech recognition component indicates that a second vocabulary from a different application will be utilized to translate the voice command and, in response to determining that the speech recognition component indicates that the second vocabulary from the different application will be utilized, load the different application, utilize the different application to translate the voice command, and perform the functional action that fulfills the voice command.

18. The vehicle speech recognition system of claim 14, wherein the logic further causes the processor to provide a user option to define a stored launch command.