Phonetic searching

• US 7,475,065 B1
• Filed: 12/11/2006
• Issued: 01/06/2009
• 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): Hudspeth; David R
• Assistant Examiner(s): Sked; Matthew J.
• Application Number:
  US11/609,127
• Time in Patent Office: 757 Days
• Field of Search: 704/236
• US Class Current: 1/1
• 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 inputting and processing a search string comprising:

entering the search string, including entering terms in said string using a first term that is linguistically specified and a second term that is entered using one or both of a term specified phonetically using delimited terms from a phonetic alphabet and a term specified by a voice command; and

searching an audio source to determine scores for said search string at locations in the audio source, including for each of multiple location of the string determining a match score characterizing the likelihood that the search string is present at that location.

2. The method of claim 1 wherein said search string is entered using Boolean logic.

3. The method of claim 2 wherein said search string is entered using a separation distance between the terms.

4. The method of claim 2 further comprising the step of converting said search string into a phonetic string, and searching said source phonetically.

5. The method of claim 4 wherein said audio source comprises a phonetic file.

6. The method of claim 4 further comprising designating that particular terms in said search string are designated by terms from a phonetic alphabet by appending a predetermined character or delimiter to such terms.

7. The method of claim 1 wherein the second term is entered using a term specified phonetically using delimited terms from a phonetic alphabet.

8. The method of claim 1 wherein the second term is specified using a voice command.