Phonetic searching

• US 7,406,415 B1
• Filed: 12/11/2006
• Issued: 07/29/2008
• Est. Priority Date: 03/04/2000
• Status: Expired due to Term

• Current Assignee: Georgia Institute of Technology (University System of Georgia), Georgia Tech Research Corporation (University System of Georgia)
• Original Assignee: Georgia Tech Research Corporation (University System of Georgia)
• Inventors: Cardillo, Peter S., Price, William E., Clements, Mark A.
• Primary Examiner(s): MCFADDEN, SUSAN IRIS
• Application Number:
  US11/609,146
• Time in Patent Office: 596 Days
• Field of Search: 704/236
• US Class Current: 704/236
• CPC Class Codes: G06F 16/3343 using phonetics
• CPC Class Codes: G06F 16/685 using automatically derived transcript of audio data, e.g. lyrics speech recognition G10L15/00
• CPC Class Codes: G10L 13/08 Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination
• CPC Class Codes: G10L 15/187 Phonemic context, e.g. pronunciation rules, phonotactical constraints or phoneme n-grams
• CPC Class Codes: Y10S 707/99933 Query processing, i.e. searching
• CPC Class Codes: Y10S 707/99934 Query formulation, input preparation, or translation
• CPC Class Codes: Y10S 707/99935 Query augmenting and refining, e.g. inexact access

Abstract

An improved method and apparatus is disclosed which uses probabilistic techniques to map an input search string with a prestored audio file, and recognize certain portions of a search string phonetically. An improved interface is disclosed which permits users to input search strings, linguistics, phonetics, or a combination of both, and also allows logic functions to be specified by indicating how far separated specific phonemes are in time.

Claims

1. A method of using a search string comprising:

specifying a search string, including

specifying linguistic items to be searched for, and

specifying a distance in time within which at least some of said linguistic items should occur in a media source; and

searching for the search string in the media source, including

determining a first quantity related to a probability that the search string occurred at a first time in the media source.

2. The method of claim 1 wherein specifying the search string further includes:

specifying a linguistically based distance within which at least some of said linguistic items should occur.

3. The method of claim 2, wherein the linguistically-based distance comprises a distance specified using units including at least one of words and sentences.

4. The method of claim 1 wherein specifying the distance in time comprises specifying a maximum separation in time.

5. The method of claim 1 wherein specifying linguistic items includes specifying words.

6. The method of claim 5 wherein specifying words includes at least one of specifying a word linguistically and specifying a word phonetically.

7. The method of claim 1 wherein the media source comprises an audio source.

8. The method of claim 1 wherein searching for the search string in the media source further includes determining corresponding quantities related to probabilities that the search string occurred at each of a plurality of times in the media source.

9. A method for searching an audio source comprising:

accepting a search string specified using Boolean logic, wherein the search string comprises terms and one or more connectors, wherein at least one of the connectors specifies a time-based relationship between terms; and

searching the audio source according to the accepted search string, including determining a quantity related to a probability that the search string occurred in the audio source.

10. The method of claim 9 further comprising:

processing an audio signal to form the audio source.

11. The method of claim 9 wherein the time-based relationship comprises a maximum separation in time between terms.

12. The method of claim 11 wherein searching the audio source includes identifying occurrences of terms of the search string that occur together within the maximum separation in time.