System and method for providing speech recognition using personal vocabulary in a network environment

• US 9,201,965 B1
• Filed: 09/30/2009
• Issued: 12/01/2015
• Est. Priority Date: 09/30/2009
• Status: Active Grant

• Current Assignee: Cisco Technology, Inc. (Cisco Systems, Inc.)
• Original Assignee: Cisco Technology, Inc. (Cisco Systems, Inc.)
• Inventors: Gannu, Satish K., Jouret, Guido, Malegaonkar, Ashutosh A.
• Primary Examiner(s): JACKSON, JAKIEDA R
• Application Number:
  US12/571,414
• Time in Patent Office: 2,253 Days
• Field of Search: 704/235
• US Class Current: 1/1
• CPC Class Codes: G06F 16/635 Filtering based on additional data, e.g. user or group profiles
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation

Abstract

A method is provided in one example and includes receiving a media file and generating a text file based on the media file. The method includes identifying selected words within the text file based on a whitelist, the whitelist includes a plurality of designated words to be tagged. The selected words are compared to a group of words associated with an individual. One or more of the selected words are removed based on the selected words not being found in the group of words associated with the individual. In more specific embodiments, the method includes generating a resultant after removing one or more of the selected words, the resultant can be separated into fields that identify a title and an author associated with the resultant. At least one of the selected words that is removed is associated with a false positive associated with two words that phonetically sound similar.

Claims

1. A method, comprising:

receiving data propagating in a network environment;

ignoring Joint Photographic Experts Group (JPEG) documents in the data;

identifying an audio and video media file in the data, wherein the audio and video media file is associated with a plurality of individuals;

generating a text file based on the audio and video media file;

comparing the text file to a plurality of blacklisted words;

dropping the text file if a blacklisted word is found in the text file;

identifying, using a processor, selected words within the text file based on a whitelist to create a first word list, wherein the first word list includes fewer words than the text file;

comparing the selected words in the first word list to a personal vocabulary database associated with an individual from the plurality of individuals, wherein the personal vocabulary database associated with the individual includes one or more words that the individual added to the personal vocabulary database, and wherein words in the personal vocabulary database associated with the individual may be marked as private; and

removing from the first word list, one or more of the selected words to create a second word list based on the selected words not being found in the personal vocabulary database associated with the individual, wherein the second word list includes fewer words then the first word list, wherein at least one of the selected words that is removed is associated with a false positive from two words that phonetically sound similar.

2. The method of claim 1, further comprising:

generating a resultant after removing one or more of the selected words, wherein the resultant is separated into fields that identify a title and an author associated with the resultant.

3. The method of claim 1, wherein the personal vocabulary database is associated with a personal vocabulary segment for the individual, and wherein the selected words that are tagged and not removed are added to the personal vocabulary segment.

4. The method of claim 1, further comprising:

providing a search interface configured to initiate a search for particular subject areas within a database that includes at least some of the selected words.

5. The method of claim 1, wherein generating the text file includes identifying audio information within the media file and converting an audio stream associated with the media file to a phonetic audio track, wherein the phonetic audio track is searched for the selected words.

6. The method of claim 1, further comprising:

receiving a query to search for one or more files based on the selected words that are tagged and not removed.

7. Logic encoded in one or more non-transitory media that includes code for execution and when executed by a processor is operable to perform operations comprising:

receiving data propagating in a network environment;

ignoring Joint Photographic Experts Group (JPEG) documents in the data;

identifying an audio and video media file in the data, wherein the audio and video media file is associated with a plurality of individuals;

generating a text file based on the audio and video media file;

comparing the text file to a plurality of blacklisted words;

dropping the text file if a blacklisted word is found in the text file;

identifying selected words within the text file based on a whitelist to create a first word list, wherein the first word list includes fewer words than the text file;

comparing the selected words in the first word list to a personal vocabulary database associated with an individual from the plurality of individuals, wherein the personal vocabulary database associated with the individual includes one or more words that the individual added to the personal vocabulary database, and wherein words in the personal vocabulary database associated with the individual may be marked as private; and

removing from the first word list, one or more of the selected words to create a second word list based on the selected words not being found in the personal vocabulary database associated with the individual, wherein the second word list includes fewer words then the first word list, wherein at least one of the selected words that is removed is associated with a false positive from two words that phonetically sound similar.

8. The logic of claim 7, the processor being further operable to perform operations comprising:

generating a resultant after removing one or more of the selected words, wherein the resultant is separated into fields that identify a title and an author associated with the resultant.

9. The logic of claim 7, wherein the personal vocabulary database is associated with a personal vocabulary segment for the individual, and wherein the selected words that are tagged and not removed are added to the personal vocabulary segment.

10. The logic of claim 7, the processor being further operable to perform operations comprising:

generating one or more thumbnails related to the media file, wherein the thumbnails are stored in a memory element.

11. The logic of claim 7, wherein generating the text file includes identifying audio information within the media file and converting an audio stream associated with the media file to a phonetic audio track, wherein the phonetic audio track is searched for the selected words.

12. The logic of claim 7, the processor being further operable to perform operations comprising:

receiving a query to search for one or more files based on the selected words that are tagged and not removed.

13. An apparatus, comprising:

a memory element configured to store data;

a processor operable to execute instructions associated with the data;

a network sensor configured to interface with the memory element and the processor, the network sensor being configured to;

receive data propagating in a network environment;

ignore Joint Photographic Experts Group (JPEG) documents in the data;

identify an audio and video media file in the data, wherein the audio and video media file is associated with a plurality of individuals;

generate a text file based on the audio and video media file;

compare the text file to a plurality of blacklisted words;

drop the text file if a blacklisted word is found in the text file;

identify selected words within the text file based on a whitelist to create a first word list;

compare the selected words in the first word list to a personal vocabulary database associated with an individual from the plurality of individuals, wherein the personal vocabulary database associated with the individual includes one or more words that the individual added to the personal vocabulary database, and wherein words in the personal vocabulary database associated with the individual may be marked as private; and

remove from the first word list one or more of the selected words to create a second word list based on the selected words not being found in the personal vocabulary database associated with the individual, wherein the second word list includes fewer words then the first word list, wherein at least one of the selected words that is removed is associated with a false positive from two words that phonetically sound similar.

14. The apparatus of claim 13, wherein a resultant is generated after removing one or more of the selected words, wherein the resultant is separated into fields that identify a title and an author associated with the resultant.

15. The apparatus of claim 13, wherein the personal vocabulary database is associated with a personal vocabulary segment for the individual, and wherein the selected words that are tagged and not removed are added to the personal vocabulary segment.

16. The apparatus of claim 13, wherein generating the text file includes identifying audio information within the media file and converting an audio stream associated with the media file to a phonetic audio track, wherein the phonetic audio track is searched for the selected words.

17. The apparatus of claim 13, further comprising:

a search module configured to receive a query to search for one or more files based on the selected words that are tagged and not removed.

18. The apparatus of claim 17, further comprising:

a search interface configured to initiate a search for particular subject areas within a database that includes at least some of the selected words.