Methods and apparatuses for identifying audible samples for use in a speech recognition capability of a mobile device

• US 8,538,760 B2
• Filed: 07/13/2010
• Issued: 09/17/2013
• Est. Priority Date: 07/13/2010
• Status: Expired due to Fees

• Current Assignee: Qualcomm, Inc.
• Original Assignee: Qualcomm, Inc.
• Inventors: Khorashadi, Behrooz, Das, Saumitra Mohan
• Primary Examiner(s): Shah, Paras D
• Application Number:
  US12/835,329
• Publication Number:
  US 20120016670A1
• Time in Patent Office: 1,162 Days
• Field of Search: 704/231, 704/9, 704/257, 704/275, 704/270, 379/88.01, 701/532, 701/539, 701/400, 701/540, 701/426, 701/409, 701/427, 701/434
• US Class Current: 704/275
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 2015/221 Announcement of recognition results

Abstract

Techniques for provided which may be implemented using various methods and/or apparatuses in a mobile device to allow for speech recognition based, at least in part, on context information associated with at least a portion of at least one navigational region, e.g., associated with a location of the mobile device. A speech recognition capability may, for example, be provided with a set of audible samples based, at least in part, on the context information. Such speech recognition capability may be provided by the mobile device and/or by one or more other devices coupled to the mobile device.

Claims

1. A method comprising:

at a mobile device;

accessing an electronic map comprising a plurality of ordered informational layers representing a plurality of navigational regions within a building, wherein at least one of said plurality of ordered informational layers is indicative of items of interest that is at least partially located within and/or associated with at least a portion of at least one of said plurality of navigational layers, said items of interest comprising and/or identifying a person, an event, and a product;

determining an initial set of audible samples for use by a speech recognition capability provided at said mobile device based, at least in part, on said electronic map; and

in response to a determination that said mobile device is located within or near at least a portion of said at least one of said plurality of navigation regions based, at least in part, on receiving a wireless signal from a device provisioned as part of a wireless communication network serving at least a portion of at least one of said plurality of navigational regions, identifying a subset of said plurality of ordered informational layers; and

based, at least in part, on said subset of said plurality of ordered informational layers and said items of interest, identifying a subset of audible samples from an initial set of audible samples for use by said speech recognition capability at least while said mobile device is located within or near said portion of said at least one of said plurality of navigational regions.

2. The method as recited in claim 1, further comprising:

at said mobile device;

obtaining one or more electrical signals representing a speech sample; and

identifying a user input via said speech recognition capability using said speech sample and at least said subset of audible samples.

3. The method as recited in claim 2, further comprising:

at said mobile device;

in response to said user input, affecting an operation of at least one process within said mobile device.

4. The method as recited in claim 3, wherein said at least one process comprises a location or navigation process.

5. The method as recited in claim 1, and further comprising:

receiving at least a portion of said electronic map from at least one of;

a location based service, or a remote device.

6. The method as recited in claim 1, wherein said set of audible samples corresponds to at least one grammar.

7. An apparatus for use in a mobile device, the apparatus comprising:

means for accessing an electronic map, comprising a plurality of ordered informational layers representing a plurality of navigational regions within said a building, wherein at least one of said plurality of ordered informational layers is indicative of items of interest that is at least partially located within and/or associated with at least a portion of at least one of said plurality of navigational layers, said items of interest comprising and/or identifying a person, an event, and a product;

means for determining an initial set of audible samples for use by a speech recognition capability provided at said mobile device based, at least in part, on said electronic map; and

in response to a determination that said mobile device is located within or near at least a portion of said at least one of said plurality of navigation regions based, at least in part, on receiving a wireless signal from a device provisioned as part of a wireless communication network serving at least a portion of at least one of said plurality of navigational regions, means for identifying a subset of said plurality of ordered informational layers; and

based, at least in part on said subset of said plurality of ordered informational layers and said items of interest, means for identifying a subset of audible samples from an initial set of audible samples for use by said speech recognition capability at least while said mobile device is located within or near said portion of said at least one of said plurality of navigational regions.

8. The apparatus as recited in claim 7, further comprising:

means for obtaining a speech sample; and

means for identifying a user input based, at least in part, on information resulting from said speech recognition capability using said speech sample and at least said subset of audible samples.

9. The apparatus as recited in claim 8, further comprising:

means for affecting an operation of at least one process within said mobile device in response to said user input.

10. The apparatus as recited in claim 9, wherein said at least one process comprises a location or navigation process.

11. The apparatus as recited in claim 7, further comprising:

means for receiving at least a portion of said electronic map from at least one of;

a location based service, or a remote device.

12. The apparatus as recited in claim 7, wherein said set of audible samples corresponds to at least one grammar.

13. An apparatus for use in a mobile device, the apparatus comprising:

memory;

at least one processing unit to;

access, via said memory, an electronic map comprising a plurality of ordered informational layers representing a plurality of navigational regions within a building, wherein at least one of said plurality of ordered informational layers is indicative of items of interest that is at least partially located within and/or associated with at least a portion of at least one of said plurality of navigational layers, said items of interest comprising and/or identifying a person, an event, and a product;

determine an initial set of audible samples for use by a speech recognition capability provided at said mobile device based, at least in part, on said electronic map; and

in response to a determination that said mobile device is located within or near at least a portion of said at least one of said plurality of navigation regions based, at least in part, on receiving a wireless signal from a device provisioned as part of a wireless communication network serving at least a portion of at least one of said plurality of navigational regions, identify a subset of said plurality of ordered informational layers; and

based, at least in part, on said subset of said plurality of ordered informational layers and said items of interest identify a subset of audible samples from an initial set of audible samples for use by said speech recognition capability at least while said mobile device is located within or near said portion of said at least one of said plurality of navigational regions.

14. The apparatus as recited in claim 13, further comprising:

a microphone; and

wherein said at least one processing unit to further access a speech sample obtained via said microphone, and identify a user input based, at least in part, on information resulting from said speech recognition capability using said speech sample and at least said subset of audible samples.

15. The apparatus as recited in claim 14, wherein said at least one processing unit to further affect an operation of at least one process within said mobile device in response to said user input.

16. The apparatus as recited in claim 15, wherein said at least one process comprises a location or navigation process.

17. The apparatus as recited in claim 13, further comprising:

a network interface; and

wherein said at least one processing unit to further obtain at least a portion of said electronic map via said network interface from at least one of;

a location based service, or a remote device.

18. The apparatus as recited in claim 13, wherein said set of audible samples corresponds to at least one grammar.

19. An article comprising:

a non-transitory computer readable medium having stored therein computer implementable instructions executable by one or more processing units of a mobile device to;

access an electronic map comprising a plurality of ordered informational layers representing a plurality of navigational regions within said a building, wherein at least one of said plurality of ordered informational layers is indicative of items of interest that is at least partially located within and/or associated with at least a portion of at least one of said plurality of navigational layers, said items of interest comprising and/or identifying a person, an event, and a product;

determine an initial set of audible samples for use by a speech recognition capability provided at said mobile device based, at least in part, on said electronic map; and

in response to a determination that said mobile device is located within or near at least a portion of said at least one of said plurality of navigation regions based, at least in part, on receiving a wireless signal from a device provisioned as part of a wireless communication network serving at least a portion of at least one of said plurality of navigational regions, identify a subset of said plurality of ordered informational layers; and

based, at least in part, on said subset of said plurality of ordered informational layers and said items of interest, identify a subset of audible samples from an initial set of audible samples for use by said speech recognition capability at least while said mobile device is located within or near said portion of said at least one of said plurality of navigational regions.

20. The article as recited in claim 19, wherein said computer implementable instructions are further executable by said one or more processing units to:

identify a user input based, at least in part, on information resulting from said speech recognition capability using a speech sample and at least said subset of audible samples.

21. The article as recited in claim 20, wherein said computer implementable instructions are further executable by said one or more processing units to:

affect an operation of at least one process within said mobile device in response to said user input.

22. The article as recited in claim 21, wherein said at least one process comprises a location or navigation process.

23. The article as recited in claim 19, wherein at least a portion of said electronic map is obtained from at least one of:

a location based service, or a remote device.

24. The article as recited in claim 19, wherein at least one of said set of audible samples corresponds to at least one grammar.