System and method for enabling search and retrieval operations to be performed for data items and records using data obtained from associated voice files

• US 8,326,879 B2
• Filed: 07/02/2009
• Issued: 12/04/2012
• Est. Priority Date: 01/03/2005
• Status: Active Grant

• Current Assignee: Qualcomm Atheros Incorporated (Qualcomm, Inc.)
• Original Assignee: ORB Networks Incorporated (Qualcomm, Inc.)
• Inventors: Julia, Luc, Guion, Alexandre, Le Nerriec, Johan, Cortina, Rafael, Marth, Stephen
• Primary Examiner(s): Woo, Isaac M
• Application Number:
  US12/497,442
• Publication Number:
  US 20090271380A1
• Time in Patent Office: 1,251 Days
• Field of Search: 707600-899
• US Class Current: 707/791
• CPC Class Codes: G06F 16/5866 using information manually generated, e.g. tags, keywords, comments, manually generated location and time information
• CPC Class Codes: G06F 16/685 using automatically derived transcript of audio data, e.g. lyrics speech recognition G10L15/00
• CPC Class Codes: G06F 16/7867 using information manually generated, e.g. tags, keywords, comments, title and artist information, manually generated time, location and usage information, user ratings
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: Y10S 707/99942 Manipulating data structure, e.g. compression, compaction, compilation
• CPC Class Codes: Y10S 707/99943 Generating database or data structure, e.g. via user interface
• CPC Class Codes: Y10S 707/99944 Object-oriented database structure
• CPC Class Codes: Y10S 707/99945 Object-oriented database structure processing
• CPC Class Codes: Y10S 707/99948 Application of database or data structure, e.g. distributed, multimedia, or image

Abstract

A method and system are provided for using the contents of voice files as a basis for enabling search and other selection operations for data items that are associated with those voice files. Voice files may be received having associations with other data items, such as images or records. A corresponding text file is generated for each of the one or more voice files using programmatic means, such as a speech-to-text application. Each text file is provided an association with a data item based on the association of the voice file that served as the basis of its creation. Each text file is then made available for the performance of search and selection operations that result in the identification of associated data items.

Claims

1. A system for enabling the identification of data items based on voice data created with the data items, the system comprising:

an interface module configured to receive a plurality of data items that each include or are associated with voice data, wherein the interface module communicates with a speech-to-text application to cause (i) a resulting text file to be generated for each of the plurality of data items, and (ii) stored in association with each of the plurality of data items;

a presentation module that is configured to identify a text selection criteria from a user input, and to perform a comparison operation on each of the text files generated from the voice data in order to determine whether the text file satisfies the text selection criteria;

wherein the data item corresponds to one of an audio file, a video file, or an image file.

2. The system of claim 1, wherein the presentation module is configured to generate a presentation based on one or more of the plurality of data items for which there are text files that satisfy the text selection criteria.

3. The system of claim 2, wherein the presentation generated by the presentation module corresponds to a slide show in which each data item in the one or more data items is rendered in a sequence.

4. The system of claim 1, wherein the interface module is configured to receive a digital image as one of the plurality of data items.

5. The system of claim 1, wherein the presentation module is configured to determine which of the plurality of data items satisfy the text selection criteria by comparing the text selection criteria to a content of each of the one or more text files associated with the one or more data items, wherein the content of each of the one or more text files includes one or more character strings.

6. The system of claim 5, wherein the presentation module receives two or more search terms as the text selection criteria, and wherein the presentation module is configured to use the two or more search terms and a BOOLEAN connector relating to the two or more search terms to identify which data items in the plurality of data items satisfy the text selection criteria.