Unified interface and routing module for handling audio input

• US 8,995,625 B2
• Filed: 09/30/2009
• Issued: 03/31/2015
• Est. Priority Date: 09/30/2009
• Status: Active Grant

• Current Assignee: T-Mobile USA, Inc. (Deutsche Telekom AG)
• Original Assignee: T-Mobile USA, Inc. (Deutsche Telekom AG)
• Inventors: Vance, Michael Steffen, Goulart, Valerie Lynn, Mann, Jonathan L., Panchal, Prarthana H., Wood, Paula H., Temple, Sinclair M., Morrison, Andrew R., Birand, Glay A.
• Primary Examiner(s): ZENATI, AMAL S
• Application Number:
  US12/570,945
• Publication Number:
  US 20110075818A1
• Time in Patent Office: 2,008 Days
• Field of Search: 379/88.01, 379/88.02, 379/88.03, 379/355, 704/270, 704/9, 704/10, 704/231, 704/251, 704/270.1, 704/257
• US Class Current: 379/88.01
• CPC Class Codes: G10L 15/07 to the speaker
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: H04M 1/72403 with means for local support of applications that increase the functionality
• CPC Class Codes: H04M 2250/74 with voice recognition means

Abstract

Methods, systems and articles for receiving, by a telecommunication device, audio input through a unified audio interface are disclosed herein. The telecommunication device is further configured to determine whether to handle the audio input as a command, as a request of a telecommunication device application, or as a network search request, the determining being based on one or more user-configurable rules or priorities.

Claims

1. A method implemented in a telecommunication device, the method comprising:

receiving audio input through a unified audio interface of the telecommunication device;

determining whether to handle the audio input as a command, as a request of a telecommunication device application, or as a network search request, the determining being based on one or more user-configurable rules or priorities;

determining that the audio input lacks a parameter for the determined one of the command, the request of the telecommunication device application, or the network search request;

in response to determining that the audio input lacks the parameter, supplementing the audio input with an execution context of the telecommunication device to be used in place of the lacking parameter; and

executing the audio input supplemented with the execution context as the determined one of the command, the request of the telecommunication device application, or the network search request.

2. The method of claim 1, further comprising:

receiving an indication that a dedicated key of the unified audio interface has been pressed or actuated, the dedicated key being reserved for invoking an audio capture process; and

in response to receiving the indication, invoking an audio capture process.

3. The method of claim 2, wherein the dedicated key is a graphic user interface (GUI) key available on each user interface (UI) screen rendered by the telecommunication device.

4. The method of claim 1, further comprising processing, by an audio recognition module, the audio input to translate the audio input from audio to text.

5. The method of claim 4, further comprising learning, by the audio recognition module, voice characteristics of a speaker to improve audio recognition.

6. The method of claim 5, wherein the processing includes retrieving the audio characteristics, the voice characteristics belonging to a speaker profile that is stored on a server and associated with a user login and/or user service agreement.

7. The method of claim 1, wherein the user-configurable rules or priorities include one or more of a priority for attempting to handle audio input as a command before handling it as a request, a priority for attempting to handle audio input as a request of a telecommunication device application before handling it as a network search request, or a priority for attempting to handle audio input as a network search request before handling it as a request of a telecommunication device application.

8. The method of claim 1, wherein the determining includes determining whether the audio input comprises one or more recognized command words or one or more words associated with telecommunication-device-level macros.

9. The method of claim 1, wherein the executing comprises executing the audio input supplemented by the execution context as a command, and executing the the audio input supplemented by the execution context as a command comprises carrying out the command on a telecommunication device setting or a telecommunication device personalization.

10. The method of claim 9, wherein the carrying out further comprises querying a service provider for account information.

11. The method of claim 1, further comprising exposing an application programming interface (API) that enables user-installed telecommunication device applications to register with and/or interact with an audio routing module of the telecommunication device which performs the determining.

12. The method of claim 1, further comprising providing potential meanings of the audio input to resolve the meaning of the audio input when the meaning of the audio input is ambiguous.

13. The method of claim 1, further comprising:

gathering context information about the telecommunication device; and

performing the determining based at least in part on the context information or submitting the context information with a command or with a request.

14. The method of claim 1, further comprising:

receiving results of the execution of the determined one of the command, request of the telecommunication device application, or network search request.

15. A telecommunication device comprising:

a processor;

an audio recognition module operable by the processor, the audio recognition module configured to recognize audio input, wherein the recognizing comprises utilizing context information associated with the telecommunication device in response to the audio recognition module determining that the audio input does not match any command of the telecommunication device or registered command or macro of telecommunication device applications; and

an audio routing module operable by the processor and configured to;

evaluate the recognized audio input to determine whether to handle the recognized audio input as a command, as a request of a telecommunication device application, or as a network search request, wherein the determined one of the command, request of the telecommunication device application, or network search request being based on user-configurable rules or priorities, the user-configurable rules or priorities including;

a first priority for attempting to handle audio input as an audio command before handling it as a request of a telecommunication device application or as a network search request, and a second priority for attempting to handle audio input as a request of a telecommunication device application before handling it as a network search request; and

executing the recognized audio input as the determined command, request of the telecommunication device application, or the network search request.

16. The telecommunication device of claim 15, wherein the audio routing module offers an application programming interface which enables user-installed telecommunication device applications to register with and/or interact with the audio routing module by providing recognized commands or macros for use by the audio routing module.

17. An article of manufacture comprising:

one or more storage devices; and

executable instructions stored on the storage devices which, when executed by a telecommunication device, instruct the telecommunication device to perform operations including;

receiving while engaged in communication with another device, an actuation of a dedicated key associated with a unified audio interface for audio commands and requests;

processing audio input provided with the actuation as an audio command or request; and

determining whether to handle the audio input as an audio command, as a request of a telecommunication device application, or as a network search request, the determining being based on user-configurable rules or priorities, the user-configurable rules or priorities including;

a first priority for attempting to handle audio input as an audio command before handling it as a request of a telecommunication device application or as a network search request, and

a second priority for attempting to handle audio input as a request of a telecommunication device application before handling it as a network search request; and

providing results of the command or request both to a user of the telecommunication device and to the other device.

18. The article of claim 17, wherein the communication with the other device is one of a phone call, a chat session, an instant messaging session, or an email message and engaging in the communication includes writing the communication, speaking the communication, reading the communication, and/or listening to the communication.