Using speech recognition results based on an unstructured language model in a mobile communication facility application
A method and system for entering information into a software application resident on a mobile communication facility is provided. The method and system may include recording speech presented by a user using a mobile communication facility resident capture facility, transmitting the recording through a wireless communication facility to a speech recognition facility, transmitting information relating to the software application to the speech recognition facility, generating results utilizing the speech recognition facility using an unstructured language model based at least in part on the information relating to the software application and the recording, transmitting the results to the mobile communications facility, loading the results into the software application and simultaneously displaying the results as a set of words and as a set of application results based on those words.
1. A method of processing speech, comprising:
receiving, at a speech recognition facility, a recording of speech presented by a user using a mobile communication facility resident capture facility, wherein the recording is transmitted through a wireless communication;
receiving contextual information relating to a software application at the speech recognition facility, wherein the contextual information originated from the mobile communication facility resident capture facility;
generating results at the speech recognition facility using an unstructured language model based, at least in part, on the contextual information relating to the software application and the recording, wherein the contextual information includes an identity of the mobile communication facility, an identity of a non-speech recognition application resident on the mobile communication facility and a usage history of the non-speech recognition application resident on the mobile communication facility, and wherein user feedback is used to adapt the unstructured language model; and
transmitting the results to the mobile communications facility, wherein the mobile communication facility is configured to receive the results at the software application and is further configured to simultaneously display the results as a set of words and as a set of application results based on those words.
2. The method of claim 1 , wherein the contextual information includes at least one of an identity of the currently active application, an identity of a text box within an application, information within an application, an identity of content resident on the mobile communication facility, and an identity of the user.
3. The method of claim 1 , wherein the software application is selected from the group consisting of a communications application, a navigation application, a search application, a mapping application, a game and an enterprise software application.
4. The method of claim 1 , further comprising selecting the language model based on the nature of the application.
5. A method of entering information into a software application other than a speech recognition application resident on a device using a processor, comprising:
recording speech presented by a user using a device-resident capture facility;
transmitting the recording through a wireless communication facility to a speech recognition facility;
transmitting contextual information relating to the software application to the speech recognition facility;
receiving results generated utilizing the speech recognition facility using an unstructured language model based, at least in part, on the contextual information relating to the software application and the recording, wherein the contextual information includes an identity of the mobile communication facility, an identity of a non-speech recognition application resident on the mobile communication facility and a usage history of the non-speech recognition application resident on the mobile communication facility, and wherein user feedback is used to adapt the unstructured language model;
loading the results into the software application; and
simultaneously displaying the results as a set of words and as a set of application results based on those words.
6. The method of claim 5 , further comprising allowing the user to alter the set of words.
7. The method of claim 6 , further comprising updating the application results based on the altered set of words.
8. The method of claim 7 , wherein the updating of application results is performed in response to a user action.
9. The method of claim 7 , wherein the updating of application results is performed automatically.
10. The method of claim 9 , wherein the automatic update is performed after a predefined amount of time after the user alters the set of words.
11. The method of claim 5 , wherein the application is an application which is searching for information or content based on the set of words.
12. The method of claim 5 , further comprising selecting the language model based on the nature of the application.
13. A speech processing system comprising:
a device-resident capture facility for recording speech presented by a user;
a wireless communication facility for transmitting the recording and contextual information relating to a software application to a speech recognition configured to generate results using an unstructured language model based at least in part on the contextual information relating to the software application and the recording, wherein the contextual information includes an identity of the mobile communication facility, an identity of a non-speech recognition application resident on the mobile communication facility and a usage history of the non-speech recognition application resident on the mobile communication facility, and wherein user feedback is used to adapt the unstructured language model;
the wireless communication facility, further for transmitting the results to the device;
the software application for receiving the results; and
a device display for simultaneously displaying the results as a set of words and as a set of application results based on those words.
14. The system of claim 13 , further comprising allowing the user to alter the set of words, and further comprising an updating facility for updating the application results based on the altered set of words.
15. The system of claim 14 , wherein the updating of application results is performed in response to a user action.
16. The system of claim 13 , wherein the software application is an application which is searching for information or content based on the set of words.
17. The system of claim 16 , wherein the application result is a set of relevant search matches for the set of words.
18. The system of claim 13 , further comprising a selecting facility for selecting the language model based on the nature of the software application.
19. The method of claim 1 , wherein the contextual information is selected from the group consisting of information concerning the user, and contents of the mobile communication facility.
20. The method of claim 1 , wherein the software application is selected from the group consisting of a communications application, a navigation application, a search application, a mapping application, a game and an enterprise software application.
21. The method of claim 5 , wherein the contextual information includes at least one of an identity of the currently active application, an identity of a text box within an application, information within an application, an identity of content resident on the mobile communication facility, and an identity of the user.
22. The method of claim 5 , wherein the software application is selected from the group consisting of a social network application, an application for obtaining directions, a search application, and a messaging application.
23. The system of claim 13 , wherein contextual information includes at least one of, information from a user's favorites list, information about the user's address book or contact list, content of the user's inbox, content of the user's outbox, the user's location, information currently displayed in an application.
24. The system of claim 13 , wherein the contextual information is at least one of information as to the type of software application and information as to the type of input required for the software application.
25. The method of claim 1 wherein at least one of the mobile communication facility resident capture facility and the wireless communication facility is an in-car device.
26. The method of claim 5 wherein at least one of the device-resident capture facility and the wireless communication facility is an in-car device.
27. The system of claim 13 wherein at least one of the device resident capture facility and the wireless communication facility is an in-car device.