Methods, systems, and products for indexing content

• US 20080071542A1
• Filed: 09/19/2006
• Published: 03/20/2008
• Est. Priority Date: 09/19/2006
• Status: Active Grant

• Current Assignee: Bellsouth Intellectual Property Corporation (AT&T, Inc.)
• Original Assignee: Bellsouth Intellectual Property Corporation (AT&T, Inc.)
• Inventors: Yu, Ke
• Granted Patent: US 8,694,318 B2
• Time in Patent Office: Days
• US Class Current: 704/270
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 2015/025 Phonemes, fenemes or fenones being the recognition units

Abstract

Methods, systems, and products are disclosed for indexing content. An audio stream is converted to a stream of phonemes. The stream of phonemes is filtered according to a list of popular phoneme strings. A weighting is computed for the content based on at least one popular phoneme combination occurring in the stream of phonemes. The content is indexed based on the weighting.

Claims

1. A method of indexing content, comprising:

converting an audio stream to a string of phonemes, the audio stream corresponding to video content;

filtering the string of phonemes according to a list of popular phoneme strings;

computing a weighting for the content based on at least one popular phoneme combination occurring in the string of phonemes; and

indexing the content based on the weighting.

2. A method according to claim 1, further comprising accessing a database of popular search queries and retrieving a search string phonemes corresponding to a popular search query.

3. A method according to claim 1, further comprising converting each phoneme in the string of phonemes to an amplitude and a frequency for each phonetic unit.

4. A method according to claim 1, further comprising storing in memory the popular phoneme combinations occurring in the string of phonemes.

5. A method according to claim 1, further comprising the steps of:

i) associating the popular phoneme combinations occurring in the string of phonemes to popular words; and

ii) indexing the popular words to the content.

6. A method according to claim 5, further comprising the steps of:

i) receiving a search query comprising text data; and

ii) comparing the text data to an index of popular words and selecting the content based on the weighting.

7. A method according to claim 5, further comprising the steps of:

i) receiving a search query comprising text data;

ii) converting the text data to a string of phonemes; and

iii) comparing the string pf phonemes to an index of popular phoneme combinations and selecting the content based on the weighting.

8. A system of indexing content, comprising:

an indexing application stored in memory; and

a processor communicating with the memory,

the indexing application instructing the processor to convert an audio stream to a string of phonemes and to filter the string of phonemes according to a list of popular phoneme strings, the audio stream corresponding to video content, the processor computes a weighting for the content based on at least one popular phoneme combination occurring in the string of phonemes and indexes the content based on the weighting.

9. A system according to claim 8, the indexing application further instructing the processor to access a database of popular search queries and convert each popular search query to a search string of phonemes.

10. A system according to claim 8, the indexing application further instructing the processor to convert each phoneme in the string of phonemes to an amplitude and a frequency for each phonetic unit.

11. A system according to claim 8, the indexing application further instructing the processor to store in memory the popular phoneme combinations occurring in the string of phonemes.

12. A system according to claim 8, the indexing application further instructing the processor to:

i) associate the popular phoneme combinations occurring in the string of phonemes to popular words; and

ii) index the popular words to the content.

13. A system according to claim 12, the indexing application further instructing the processor to:

i) receive a search query comprising text data; and

ii) compare the text data to an index of popular words and select the content based on the weighting.

14. A system according to claim 12, the indexing application further instructing the processor to:

i) receive a search query comprising text data;

ii) convert the text data to a search string of phonemes; and

iii) compare the search string of phonemes to an index of popular phoneme combinations and select the content based on the weighting.

15. A computer program product comprising computer-readable instructions for performing the steps:

converting an audio stream to a string of phonemes, the audio stream corresponding to video content;

filtering the string of phonemes according to a list of popular phoneme strings;

computing a weighting for the content based on at least one popular phoneme combination occurring in the string of phonemes; and

indexing the content based on the weighting.

16. A computer program product according to claim 15, further comprising instructions for accessing a database of popular search queries and converting each popular search query to a search string of phonemes.

17. A computer program product according to claim 15, further comprising instructions for converting each phoneme in the string of phonemes to an amplitude and a frequency for each phonetic unit.

18. A computer program product according to claim 15, further comprising instructions for storing in memory the popular phoneme combinations occurring in the string of phonemes.

19. A computer program product according to claim 15, further comprising instructions for:

i) associating the popular phoneme combinations occurring in the string of phonemes to popular words; and

ii) indexing the popular words to the content.

20. A computer program product according to claim 19, further comprising instructions for:

i) receiving a search query comprising text data; and

ii) comparing the text data to an index of popular words and selecting the content based on the weighting.