Methods and apparatus for audio data analysis and data mining using speech recognition

• US 8,055,503 B2
• Filed: 11/01/2006
• Issued: 11/08/2011
• Est. Priority Date: 10/18/2002
• Status: Expired due to Fees

• Current Assignee: RingCentral Incorporated
• Original Assignee: Siemens Enterprise Communications, Inc. (Atos SE)
• Inventors: Scarano, Robert, Mark, Lawrence
• Primary Examiner(s): Saint Cyr, Leonard
• Application Number:
  US11/590,772
• Publication Number:
  US 20070083370A1
• Time in Patent Office: 1,833 Days
• Field of Search: None
• US Class Current: 704/270
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: H04M 2201/40 using speech recognition speech recognition per se G10L15/00
• CPC Class Codes: H04M 3/42221 Conversation recording systems at the subscriber's set H04M1/656
• CPC Class Codes: H04M 3/5166 in combination with interactive voice response systems or voice portals, e.g. as front-ends
• CPC Class Codes: H04M 3/5183 Call or contact centers with computer-telephony arrangements

Abstract

A system and method provide an audio analysis intelligence tool with ad-hoc search capabilities using spoken words as an organized data form. An SQL-like interface is used to process and search audio data and combine it with other traditional data forms to enhance searching of audio segments to identify those audio segments satisfying minimum confidence levels for a match.

Claims

1. A method of searching audio data, comprising:

defining search criteria containing both at least one search phrase to be used in searching contents of at least one audio segment and at least one data value representing information pertaining to said at least one audio segment;

using at least one computer to search a set of audio segments for said at least one search phrase and said at least one data value; and

producing a set of results of occurrences of said at least one search phrase within said set of audio segments with information matching said at least one data value such that a given occurrence is a match for said search phrase within a minimum confidence level;

wherein said step of defining includes defining a plurality of search phrases, said step of searching includes searching said set of audio segments for said plurality of search phrases, and said step of producing includes producing a set of results of all audio segments including (i) at least one occurrence of a selected required one of said plurality of search phrases and (ii) non-occurrences of at least one selected forbidden one of said plurality of search phrases to be excluded from within said set of audio segments, said occurrence and non-occurrence determined with respect to said minimum confidence level that a given occurrence within said set of audio segments is a match for a corresponding one of said plurality of search phrases.

2. A method of searching audio data, comprising:

defining search criteria containing both at least one search phrase to be used in searching contents of at least one audio segment and at least one data value representing information pertaining to said at least one audio segment;

using at least one computer to search a set of audio segments for said at least one search phrase and said at least one data value; and

producing a set of results of occurrences of said at least one search phrase within said set of audio segments with information matching said at least one data value such that a given occurrence is a match for said search phrase within a minimum confidence level;

wherein said defining includes defining a plurality of search phrases, said searching includes searching said set of audio segments for said plurality of search phrases, and said producing includes producing a set of results of all audio segments lacking occurrences of said plurality of search phrases identified in a specified temporal relationship within said set of audio segments with said minimum confidence level that a given occurrence within said set of audio segments is a match for a corresponding one of said plurality of search phrases.

3. The method according to claim 2 wherein said temporal relationship is with respect to said plurality of search phrases.

4. The method according to claim 2 wherein said temporal relationship is with respect to said set of audio segments segment.

5. A system for searching audio data comprising:

a programmable processor containing control logic operating to (i) define at least one search phrase used in searching contents of at least one audio segment and (ii) define a minimum confidence level for searching; and

at least one search engine operating to search a set of audio segments and intrinsic data associated therewith for (i) said at least one search phrase and (ii) ones of said audio segments satisfying match criteria for said intrinsic data and, in response, produce a set of results of all occurrences of said at least one search phrase within said set of audio segments satisfying said match criteria and said minimum confidence level that a given occurrence is a match for said at least one search phrase;

wherein said control logic is further operable to define a plurality of search phrases, said at least one search engine further operable to search said set of audio segments for said plurality of search phrases and produce a set of results of all audio segments including (i) at least one occurrence of a selected required one of said plurality of search phrases and (ii) non-occurrences of at least one selected forbidden one of said plurality of search phrases to be excluded from within said set of audio segments, said occurrence and non-occurrence determined with respect to said minimum confidence level that a given occurrence within said audio segments is a match for a corresponding one of said plurality of search phrases.

6. A system for searching audio data comprising:

a programmable processor containing control logic operating to (i) define at least one search phrase used in searching contents of at least one audio segment and (ii) define a minimum confidence level for searching; and

at least one search engine operating to search a set of audio segments and intrinsic data associated therewith for (i) said at least one search phrase and (ii) ones of said audio segments satisfying match criteria for said intrinsic data and, in response, produce a set of results of all occurrences of said at least one search phrase within said set of audio segments satisfying said match criteria and said minimum confidence level that a given occurrence is a match for said at least one search phrase;

wherein said control logic is operable to define a plurality of search phrases, said at least one search engine further operable to search said set of audio segments for said plurality of search phrases and produce a set of results of all audio segments lacking occurrences of said plurality of search phrases identified in a specified temporal relationship within said set of audio segments with said minimum confidence level that a given occurrence within said set of audio segments is a match for a corresponding one of said plurality of search phrases.

7. The system according to claim 6 wherein said temporal relationship is with respect to said plurality of search phrases.

8. The system according to claim 6 wherein said temporal relationship is with respect to said set of audio segments.