Sending a communications header with voice recording to send metadata for use in speech recognition, formatting, and search mobile search application

• US 8,635,243 B2
• Filed: 08/27/2010
• Issued: 01/21/2014
• Est. Priority Date: 03/07/2007
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Blackberry Limited
• Inventors: Phillips, Michael S., Nguyen, John N.
• Primary Examiner(s): Fleurantin, Jean B
• Application Number:
  US12/870,257
• Publication Number:
  US 20110066634A1
• Time in Patent Office: 1,243 Days
• Field of Search: 707/706, 707/709, 707/758, 707/769, 707/770, 709/203, 704/7, 704/9, 704/245, 704/256.1, 704/270.1, 704/235
• US Class Current: 707/769
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: G10L 2015/228 of application context

Abstract

In embodiments of the present invention improved capabilities are described for sending a communications header with the voice recording to send metadata for use in speech recognition, formatting, and search in searching for web content on a mobile communication facility comprising capturing speech presented by a user using a resident capture facility on the mobile communication facility; transmitting a communications header to a speech recognition facility from the mobile communication facility through a wireless communications facility, wherein the communications header includes at least one of device name, network type, audio source, display parameters for the wireless communications facility, geographic location, and phone number information; transmitting at least a portion of the captured speech as data through the wireless communication facility to a speech recognition facility; generating speech-to-text results utilizing the speech recognition facility based at least in part on the information relating to the captured speech and the communications header; and transmitting text from the speech-to-text results along with URL usage information configured to enable a user to conduct a search on the mobile communication facility.

Claims

1. A method of searching for web content on a mobile communication facility comprising:

capturing, by the mobile communication facility, having one or more processors, speech presented by a user using a resident capture facility on the mobile communication facility;

transmitting, by the mobile communication facility, a communications header to a speech recognition facility from the mobile communication facility through a wireless communications facility, wherein the communications header includes at least one of device name, network type, audio source, display parameters for the wireless communications facility, geographic location, or phone number information;

transmitting, by the mobile communication facility, at least a portion of the captured speech as data through the wireless communication facility to a speech recognition facility;

receiving, by the mobile communication facility, text from the speech recognition facility from speech-to-text results generated by the speech recognition facility based at least in part on the data relating to the at least a portion of the captured speech and based on the communications header, the text including URL usage information configured to enable a user to conduct the search on the mobile communication facility, wherein the Uniform Resource Locators (URL) usage information is included for a plurality of distinct web-based search facilities; and

searching for web content on the mobile communication facility.

2. The method of claim 1, wherein the URL usage information is associated with a plurality of base URLs and includes at least one formatting rule specifying how search text is combined with a base URL to form a search URL that enables a search based on the text using the mobile communications facility.

3. The method of claim 1, wherein the mobile communication facility comprises a resident search engine for searching for the web content.

4. The method of claim 1, wherein the step of receiving comprises receiving the text from the speech recognition facility into a text field on the mobile communications facility.

5. The method of claim 1, further comprising loading the loading the text into a search application resident on the mobile communications facility.

6. A method of searching for web content on a mobile communication facility comprising:

capturing, by the mobile communication facility, having one or more processors, speech presented by a user using a resident capture facility on the mobile communication facility;

transmitting, by the mobile communication facility, a communications header to a speech recognition facility from the mobile communication facility through a wireless communications facility, wherein the communications header includes metadata with at least one of device name, a network type, an audio source, display parameters for the wireless communications facility, a geographic location, or phone number information;

transmitting, by the mobile communication facility, at least a portion of the captured speech as data through the wireless communication facility to a speech recognition facility;

receiving, by the mobile communication facility, text from the speech recognition facility from speech-to-text results generated by the speech recognition facility based at least in part on information relating to the captured speech and the communications header, the text including information configured to enable a user to conduct a search on the mobile communication facility, wherein the speech-to-text results are generated using at least one statistical language model selected from a set of language models based at least in part on the information relating to the captured speech and the communications header, wherein the received text includes URL usage information configured to enable the user to conduct the search on the mobile communication facility; and

loading the text into a search application resident on the mobile communications facility to search for the web content.

7. The method of claim 6, wherein the speech-to-text results are generated using client state information relating to the captured speech.

8. The method of claim 7, wherein the client state information comprises information selected from the group consisting of a user identification, a usage history of the search application on the mobile communications device, and a location of the mobile communications device.

9. The method of claim 6, further comprising deciding whether the at least one selected statistical language model provides insufficient recognition output for the speech-to-text results and repeating the step of receiving text from speech-to-test results, wherein the speech-to-text results are generated using at least one additional language model from the first set of language models for a subsequent step of receiving text.

10. The method of claim 6, further comprising receiving results of the search on the mobile communication facility.