Voice clip search

• US 6,697,796 B2
• Filed: 01/13/2000
• Issued: 02/24/2004
• Est. Priority Date: 01/13/2000
• Status: Expired due to Term

• Current Assignee: Avago Technologies International Sales Pte Limited (Broadcom, Inc.)
• Original Assignee: Agere Systems Incorporated (Broadcom, Inc.)
• Inventors: Kermani, Bahram Ghaffarzadeh
• Primary Examiner(s): Vu, Kim
• Assistant Examiner(s): Ly, Anh
• Application Number:
  US09/482,062
• Publication Number:
  US 20020138468A1
• Time in Patent Office: 1,503 Days
• Field of Search: 707/1-10, 386/69-70, 386/125-126, 386/95, 386/98, 386/4, 386/45, 386/111-112, 386/96, 386/104, 379/88.14, 704/278, 704/9, 704/260
• US Class Current: 1/1
• CPC Class Codes: G06F 16/40 of multimedia data, e.g. slideshows comprising image and additional audio data retrieval of still image data G06F16/50; retrieval of audio data G06F16/60; retrieval of video data G06F16/70
• CPC Class Codes: G06F 16/632 Query formulation
• CPC Class Codes: G06F 16/685 using automatically derived transcript of audio data, e.g. lyrics speech recognition G10L15/00
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: Y10S 707/99933 Query processing, i.e. searching

Abstract

A technique and apparatus to allow a digital search of the entries in a digital audio database such as the Flash memory of a telephone answering system, the hard drive of a voice messaging system, the audio tracks on a compact disk, a cassette tape, a digital video disk (DVD), a videotape, etc. In one disclosed embodiment, each entry in the digital audio database (e.g., each audio track, each voice message, etc.) is converted into textual information, and the converted textual information is associated with a particular audio segment within the digital audio database. The textual information allows a digital search to be performed for a particular voice message, or portion of a voice message, in a telephone answering device, or for a particular song on a music CD, etc. Once the particular audio segment(s) containing a particular textual string is (are) located, that particular audio segment may be played or otherwise accessed, either in whole or in relevant part. While the described embodiments relate to a telephone answering device or a compact disk player, the principles of the present invention relate equally to any search mechanism for a particular digital audio segment stored in a database.

Claims

1. A digital audio search module adaptively connected to a voice messaging system, comprising:

a voice clip search module;

a digital audio database including a plurality of audio segments;

a speech-to-text converter to produce a plurality of textual information substantially corresponding word for word to a corresponding plurality of said audio segments; and

a text storage medium including said plurality of textual information;

wherein said voice clip search module is adapted to search for a match in text in said plurality of textual information, and allow retrieval of one of said plurality of audio segments corresponding to a matched one of said plurality of textual information stored in said voice messaging system.

2. The digital audio search module according to claim 1, wherein:

each of said plurality of textual information is time stamped.

3. The digital audio search module according to claim 1, wherein:

said association is based on a relative time from a start of playback of said relative audio segment.

4. The digital audio search module according to claim 1, wherein:

said digital audio database is formed in Flash memory.

5. The digital audio search module according to claim 1, wherein:

said digital audio database is formed in an optical disk.

6. The digital audio search module according to claim 1, wherein:

said digital audio database is formed in a hard drive.

7. A method of marking individual entries of a digital audio storage medium for textual search, comprising:

converting with a speech-to-text converter to produce a plurality of textual information substantially corresponding word for word to a plurality of audio segments;

associating individual text produced by said speech-to-text converter to with each of a plurality of portions of each audio segment stored in said digital audio storage medium;

providing a time stamp with each associated individual text; and

searching said associated individual text for a user provided text string;

wherein said digital audio storage medium is adaptively connected to a voice messaging system.

8. The method of marking individual entries of a digital audio storage medium for textual search according to claim 7, wherein:

said digital audio storage medium is a compact disk.

9. A method of searching for an individual audio segment stored on a digital audio storage medium adaptively connected to a voice messaging system, comprising:

converting an individual audio segment from speech to converted text;

entering a desired text string for search;

searching a text storage medium containing said converted text for at least a close match of said desired text string; and

determining a location of a corresponding audio portion of said desired text string in said individual audio segment stored on said digital audio storage medium adaptively connected to said voice messaging system.

10. The method of searching for an individual audio segment stored on a digital audio storage medium according to claim 9, further comprising:

playing said audio segment starting from a beginning of said audio segment.

11. The method of searching for an individual audio segment stored on a digital audio storage medium according to claim 9, further comprising:

playing said audio segment starting from said corresponding audio portion.

12. The method of searching for an individual audio segment stored on a digital audio storage medium according to claim 9, wherein said step of entering comprises:

performing voice-to-text conversion of a search string spoken by a user.

13. Apparatus for marking individual entries of a digital audio storage medium for textual search, comprising:

means for converting with a speech-to-text converter to produce a plurality of textual information substantially corresponding word for word to a plurality of audio segments;

means for associating individual text produced by said speech-to-text converter to with each of a plurality of portions of each audio segment stored in said digital audio storage medium;

means for providing a time stamp with each associated individual text; and

means for searching said associated individual text for a user provided text string;

wherein said digital audio storage medium is adaptively connected to a voice messaging system.

14. Apparatus for marking individual entries of a digital audio storage medium for textual search according to claim 13, wherein:

said digital audio storage medium is a compact disk.

15. Apparatus for searching for an individual audio segment stored on a digital audio storage medium adaptively connected to a voice messaging system, comprising:

means for converting an individual audio segment from speech to converted text;

means for entering a desired text string for search;

means for searching a text storage medium containing said converted text for at least a close match of said desired text string; and

means for determining a location of a corresponding audio portion of said desired text string in said individual audio segment stored on said digital audio storage medium adaptively connected to said voice messaging system.

16. The apparatus for marking individual entries of a digital audio storage medium for textual search according to claim 15, wherein said means for entering comprises:

means for performing voice-to-text conversion of a search string spoken by a user.