DIGITAL MEDIA VOICE TAGS IN SOCIAL NETWORKS

• US 20110219018A1
• Filed: 03/05/2010
• Published: 09/08/2011
• Est. Priority Date: 03/05/2010
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Erickson, Thomas D., Christensen, James E., Bailey, Mark, Kellogg, Wendy A., Ellis, Jason B., Danis, Catalina M., Farrell, Robert G.
• Granted Patent: US 8,903,847 B2
• Time in Patent Office: Days
• US Class Current: 707/769
• CPC Class Codes: G06F 16/50 of still image data
• CPC Class Codes: G10L 15/10 using distance or distortion measures between unknown speech and reference templates
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 17/00 Speaker identification or verification techniques
• CPC Class Codes: G10L 2015/025 Phonemes, fenemes or fenones being the recognition units
• CPC Class Codes: H04M 2203/303 Marking
• CPC Class Codes: H04M 3/4936 Speech interaction details speech recognition per se G10L15/00
• CPC Class Codes: Y10S 707/915 Image
• CPC Class Codes: Y10S 707/916 Audio

Abstract

A voice tagging system includes a client computing device that includes a media object capture device and a voice capture device and runs a client application that associates media objects to voice samples. The system also includes a communications network coupled to the client computing device, a voice tagging system coupled to the communications network and receiving at least one association between a first media object and a first voice sample, and a database coupled to the voice tagging system, the database including one or more voice tags, each voice tag being coupled to one or more voice samples.

Claims

1. A system comprising:

a client computing device, the client computing device including a media object capture device and a voice capture device and running a client application that associates media objects to voice samples;

a communications network coupled to the client computing device;

a voice tagging system coupled to the communications network and receiving at least one association between a first media object and a first voice sample; and

a database coupled to the voice tagging system, the database including one or more voice tags, each voice tag being coupled to one or more voice samples.

2. The system of claim 1, wherein at least one voice sample stored in the database has a phoneme representation.

3. The system of claim 2, wherein the at least one voice sample is linked to a speaker identifier.

4. The system of claim 1, wherein the client computing device is a cellular phone.

5. The system of claim 1, wherein multiple voice samples having similar phoneme representations are linked to one voice tag.

6. The system of claim 1, wherein the first media object is an image.

7. A method of tagging media objects, the method comprising:

receiving at a server an association between a first voice sample and a first media object;

comparing the first voice sample to one or more other voice samples;

linking the first voice sample to a first voice tag;

linking the first voice tag to the first media object; and

storing the first voice sample, the first voice tag, the first media object and any links between them in a database coupled to the server.

8. The method of claim 7, wherein the association is received from a cellular phone.

9. The method of claim 8, wherein the first media object is created at the cellular phone.

10. The method of claim 8, wherein the first media object is retrieved from the database and presented on the cellular phone.

11. The method of claim 7, wherein comparing includes:

forming a first phoneme representation for the first voice sample; and

comparing the first phoneme representation to other phoneme representations linked to the one or more other voice samples.

12. The method of claim 11, wherein, in the event that the first phoneme representation matches one of the one or more other voice samples, the first voice sample is linked to the first voice tag, the first voice tag previously being linked to the one of the one or more other voice samples.

13. The method of claim 11, wherein, in the event that the first phoneme representation does not match one of the one or more other voice samples, linking the first voice sample to the first voice tag further includes:

creating the first tag after it is determined that the first phoneme representation does not match one of the one or more other voice samples.

14. The method of claim 8, further comprising:

storing the first media object in the database.

15. The method of claim 8, further comprising:

linking the first voice tag to a second media object.

16. A method of searching a digital database containing voice tagged media objects, the method comprising:

receiving a first audio search at a server;

comparing the first audio search to digital representations of voice tags stored in the digital database; and

returning one or more media objects linked to voice tags matching the first audio search.

17. The method of claim 16, wherein the first audio search is received from a cellular telephone.

18. The method of claim 16, wherein comparing includes:

converting the first audio search to a first phoneme representation; and

calculating a similarity score between the first phoneme representation and other phoneme representations linked to the voice tags.

19. The method of claim 18, wherein the similarity score is based on a beginning portion of the first phoneme representation.

20. The method of claim 16, wherein returning includes:

replaying the at least a portion of the first audio search.