Methods and nodes for enabling and producing input to an application

• US 9,576,572 B2
• Filed: 06/18/2012
• Issued: 02/21/2017
• Est. Priority Date: 06/18/2012
• Status: Active Grant

• Current Assignee: Telefonaktiebolaget LM Ericsson
• Original Assignee: Telefonaktiebolaget LM Ericsson
• Inventors: Arkko, Jari, Menp, Jouni, Mecklin, Tomas
• Primary Examiner(s): ABEBE, DANIEL DEMELASH
• Application Number:
  US14/408,756
• Publication Number:
  US 20150199961A1
• Time in Patent Office: 1,709 Days
• Field of Search: 704/275
• US Class Current: 1/1
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G10L 15/08 Speech classification or search
• 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 2015/088 Word spotting
• CPC Class Codes: G10L 2015/228 of application context

Abstract

Methods and nodes for enabling and producing input generated by speech of a user, to an application. When the application has been activated (2:1), an application node (200) detects (2:2) a current context of the user and selects (2:3), from a set of predefined contexts (204a), a predefined context that matches the detected current context. The application node (200) then provides (2:4) keywords associated with the selected predefined context to a speech recognition node (202). When receiving (2:5) speech from the user, the speech recognition node (202) is able to recognize (2:6) any of the keyword in the speech. The recognized keyword is then used (2:7) as input to the application.

Claims

1. A method performed in an application node for enabling input to an application from speech made by a user, the method comprising:

detecting a current context of the user when said application has been activated,

selecting a predefined context that matches the detected current context of the user, wherein said predefined context pertains to status or role of the user, said status or role of the user defining authorizations of the user, and

providing at least one keyword associated with the selected predefined context to a speech recognition node, thereby enabling the speech recognition node to recognize any of the at least one keyword in said speech, wherein the recognized keyword is used as input to said application.

2. The method according to claim 1, wherein said predefined context is selected from a set of predefined contexts and associated keywords configured in the application node for the application.

3. The method according to claim 1, wherein the at least one keyword associated with the selected predefined context is provided to a user equipment operated by the user, thereby enabling the user equipment to translate any of said at least one keyword, when occurring in said speech, into a command as input to the application.

4. An application node configured to enable input from speech made by a user to an application, the application node comprising:

a detecting unit adapted to detect a current context of the user when said application has been activated,

a selecting unit adapted to select a predefined context that matches the detected current context of the user, wherein said predefined context pertains to status or role of the user, said status or role of the user defining authorizations of the user, and

a providing unit adapted to provide at least one keyword associated with the selected predefined context to a speech recognition node, thereby enabling the speech recognition node to recognize any of the at least one keyword in said speech, wherein the recognized keyword is used as input to said application.

5. The application node according to claim 4, wherein the selecting unit is further adapted to select said predefined context from a set of predefined contexts and associated keywords configured in the application node for the application.

6. The application node according to claim 4, wherein the providing unit is further adapted to provide the at least one keyword associated with the selected predefined context to a user equipment operated by the user, thereby enabling the user equipment to translate any of said at least one keyword, when occurring in said speech, into a command as input to the application.

7. A method performed in a speech recognition node for producing input to an application from speech made by a user, the method comprising:

receiving from an application node at least one keyword associated with a predefined context that matches a current context of the user, wherein said predefined context pertains to status or role of the user, said status or role of the user defining authorizations of the user,

receiving said speech made by the user,

recognizing in the received speech a keyword out of the received at least one keyword, and

using the recognized keyword as input to said application.

8. The method according to claim 7, wherein the recognized keyword is used by sending the keyword to at least one of the application and a user equipment operated by the user.

9. The method according to claim 7, wherein the keyword is recognized by using any of:

speech recognition, keyword spotting and phonetic-based search.

10. The method according to claim 7, wherein the recognized keyword is translated into a command used for controlling the application.

11. The method according to claim 7, wherein the keyword is recognized by using phonetic-based search.

12. A speech recognition node configured to produce input to an application from speech made by a user, the speech recognition node comprising:

a first receiving unit adapted to receive from an application node at least one keyword associated with a predefined context that matches a current context of the user, wherein said predefined context pertains to status or role of the user, said status or role of the user defining authorizations of the user,

a second receiving unit adapted to receive said speech made by the user,

a logic unit adapted to recognize in the received speech a keyword out of the received at least one keyword, and

a usage unit adapted to use the recognized keyword as input to said application.

13. The speech recognition node according to claim 12, wherein the usage unit is further adapted to use the recognized keyword by sending the keyword to at least one of the application and a user equipment operated by the user.

14. The speech recognition node according to claim 12, wherein the logic unit is further adapted to recognize the keyword by using any of:

speech recognition, keyword spotting and phonetic-based search.

15. The speech recognition node according to claim 12, wherein the logic unit is further adapted to translate the recognized keyword into a command used for controlling the application.

16. The speech recognition node according to claim 12, wherein the logic unit is further adapted to recognize the keyword by using phonetic-based search.