Association of context data with a voice-message component

• US 9,042,921 B2
• Filed: 02/16/2010
• Issued: 05/26/2015
• Est. Priority Date: 09/21/2005
• Status: Expired due to Fees

• Current Assignee: Buckyball Mobile, Inc.
• Original Assignee: Buckyball Mobile, Inc.
• Inventors: Karmarkar, Amit
• Primary Examiner(s): DOAN, PHUOC HUU
• Application Number:
  US12/706,296
• Publication Number:
  US 20100145702A1
• Time in Patent Office: 1,925 Days
• Field of Search: 455/466, 455/403, 4555001-5759
• US Class Current: 455/466
• CPC Class Codes: H04L 51/04 Real-time or near real-time messaging, e.g. instant messaging [IM]
• CPC Class Codes: H04L 51/58 Message adaptation for wireless communication
• CPC Class Codes: H04M 1/72433 for voice messaging, e.g. dictaphones for answering incoming calls H04M1/64
• CPC Class Codes: H04M 1/72454 according to context-related or environment-related conditions

Abstract

Disclosed are a system, method, and article of manufacture of associating a context data with a voice-message component. The context data may be encoded into a voice message signal. The context-data may be associated with the voice-message component according to an attribute of the voice message. The attribute of the voice message may include at least one of a word, a phrase, a voice timbre, a duration of a pause between two words, a volume a voice and an ambient sound voice and a duration of a pause between two words. The context data may be selected according to a meaning of the attribute of the voice-message component.

Claims

1. A method comprising:

receiving a user-generated voice-message generated with a mobile device;

converting a voice-message component into a text format;

automatically determining a meaning of the voice-message component; and

automatically determining a context data, wherein the context data describes an environmental attribute of the mobile device relating to the meaning of the voice-message component;

automatically selecting the context data according to the meaning of the attribute of the voice-message component;

acquiring the context data from a sensor of the mobile device; and

linking the context data with the voice-message component in the user-generated voice message.

2. The method of claim 1 further comprising:

encoding the context data into a voice message signal.

3. The method of claim 2, wherein the voice message comprises a short voice message.

4. The method of claim 3, wherein the attribute of the voice message comprises at least one of a word, a phrase, a voice timbre, a duration of a pause between two words, a volume of a voice and an ambient sound.

5. The method of claim 3 further comprising:

determining a meaning of the attribute of the voice-message component.

6. The method of claim 1 further comprising:

identifying at least one ambient sound of the voice message with a sound recognition algorithm.

7. The method of claim 1 further comprising:

identifying at least one speaker of the voice message with a voice recognition algorithm.

8. The method of claim 1 further comprising:

selecting the context data according to a state of a mobile device used to generate the voice message.

9. A system comprising:

a processor;

a computer-readable memory communicatively coupled with the processor;

a voice-message application resident on the computer-readable memory to generate user-generated voice message;

a context-data application to automatically determine a context-data related to a meaning of a voice-message component and to link the context-data with the voice-message component, to convert a voice-message component into a text format, to automatically determine a meaning of the voice-message component, and to automatically determine a context data, wherein the context data describes an environmental attribute of the mobile device relating to the meaning of the voice-message component; and

a sensor to automatically acquire the context data.

10. The system of claim 9,

wherein the context-data application automatically determines the meaning of the voice-message component by translating the voice-message component into a text format and uses a table to link the text format of the voice-message component to the context data type to be acquired by the sensor.

11. The system of claim 9 further comprising:

a machine-learning application to incorporate intelligence into the context-data application.