초록 ▼

A method of obtaining information using a mobile device can include receiving a request including speech data from the mobile device, and querying a network service using query information extracted from the speech data, whereby search results are received from the network service. The search result

A method of obtaining information using a mobile device can include receiving a request including speech data from the mobile device, and querying a network service using query information extracted from the speech data, whereby search results are received from the network service. The search results can be formatted for presentation on a display of the mobile device. The search results further can be sent, along with a voice grammar generated from the search results, to the mobile device. The mobile device then can render the search results.

대표청구항 ▼

1. A method comprising acts of: receiving, via at least one network, a request comprising speech data from a mobile device;dynamically building a query using the speech data;sending the query to a network service and, in response, receiving search results from the network service;using at least one

1. A method comprising acts of: receiving, via at least one network, a request comprising speech data from a mobile device;dynamically building a query using the speech data;sending the query to a network service and, in response, receiving search results from the network service;using at least one computer to dynamically create a voice grammar from the search results;creating a multi-modal markup language document comprising the search results and the voice grammar; andsending the multi-modal markup language document to the mobile device. 2. The method of claim 1, wherein the speech data is a textual representation of user speech, the method further comprising acts of: selecting at least one term from the speech data; andincluding the selected term within the query. 3. The method of claim 2, wherein the speech data is digitized audio, the method further comprising an act of speech recognizing the speech data. 4. The method of claim 1, further comprising an act of including within the multi-modal markup language document at least one different voice grammar that was previously sent to the mobile device in a prior transaction. 5. The method of claim 1, further comprising acts of: selecting at least one term from the search results;formatting the term within the multi-modal markup language document for presentation upon a display of the mobile device; andincluding the selected term within the voice grammar of the multi-modal markup language document. 6. The method of claim 5, further comprising acts of: causing the multi-modal markup language document to be executed within the mobile device; andin response to detecting a user spoken utterance specifying the term from the voice grammar, initiating a request for further information regarding the spoken term. 7. The method of claim 5, further comprising: receiving a subsequent request comprising speech data from the mobile device, wherein the subsequent request specifies the term from the search results;building a subsequent query using the term specified in the speech data of the subsequent request; andsending the subsequent query to the network service. 8. A machine readable storage device having stored thereon a computer program which, when executed by at least one computer, controls the at least one computer to carry out a method comprising: receiving, via at least one network, a request comprising speech data from a mobile device;dynamically building a query using the speech data;sending the query to a network service and, in response, receiving search results from the network service;dynamically creating a voice grammar from the search results;creating a multi-modal markup language document comprising the search results and the voice grammar; andsending the multi-modal markup language document to the mobile device. 9. The machine readable storage device of claim 8, wherein the speech data is a textual representation of user speech, the method further comprising: selecting at least one term from the speech data; andincluding the selected term within the query. 10. The machine readable storage device of claim 9, wherein the speech data is digitized audio, the method further comprising speech recognizing the speech data. 11. The machine readable storage device of claim 8, the method further comprising for including within the multi-modal markup language document at least one different voice grammar that was previously sent to the mobile device in a prior transaction. 12. The machine readable storage device of claim 8, the method further comprising: selecting at least one term from the search results;formatting the term within the multi-modal markup language document for presentation upon a display of the mobile device; andincluding the selected term within the voice grammar of the multi-modal markup language document. 13. The machine readable storage device of claim 12, the method further comprising: causing the multi-modal markup language document to be executed within the mobile device; andin response to detecting a user spoken utterance specifying the term from the voice grammar, initiating a request for further information regarding the spoken term. 14. The machine readable storage device of claim 12, the method further comprising: receiving a subsequent request comprising speech data from the mobile device, wherein the subsequent request specifies the term from the search results;building a subsequent query using the term specified in the speech data of the subsequent request; andsending the subsequent query to the network service. 15. A system comprising at least one computer programmed to: receive, via at least one network, a request comprising speech data from a mobile device;dynamically build a query using the speech data;send the query to a network service and, in response, receive search results from the network service;dynamically create a voice grammar from the search results;create a multi-modal markup language document comprising the search results and the voice grammar; andsend the multi-modal markup language document to the mobile device. 16. The system of claim 15, wherein the speech data is a textual representation of user speech, and wherein the at least one computer is further programmed to: select at least one term from the speech data; andinclude the selected term within the query. 17. The system of claim 16, wherein the speech data is digitized audio, and wherein the at least one computer is further programmed to speech recognize the speech data. 18. The system of claim 15, wherein the at least one computer is further programmed to: select at least one term from the search results;format the term within the multi-modal markup language document for presentation upon a display of the mobile device; andinclude the selected term within the voice grammar of the multi-modal markup language document. 19. The system of claim 18, wherein the at least one computer is further programmed to: cause the multi-modal markup language document to be executed within the mobile device; andin response to detecting a user spoken utterance specifying the term from the voice grammar, initiate a request for further information regarding the spoken term. 20. The system of claim 18, wherein the at least one computer is further programmed to: receive a subsequent request comprising speech data from the mobile device, wherein the subsequent request specifies the Wan from the search results;build a subsequent query using the term specified in the speech data of the subsequent request; andsend the subsequent query to the network service.