Automatic validation of recognized dynamic audio data from data provider system using an independent data source

• US 6,604,074 B2
• Filed: 03/22/2001
• Issued: 08/05/2003
• Est. Priority Date: 03/22/2001
• Status: Expired due to Term

• Current Assignee: Empirix Incorporated (Empirix Holdings I, Inc.)
• Original Assignee: Empirix Incorporated (Empirix Holdings I, Inc.)
• Inventors: Ziegelmiller, Daniel
• Primary Examiner(s): Smits, Talivaldis Ivars
• Application Number:
  US09/814,576
• Publication Number:
  US 20020138261A1
• Time in Patent Office: 866 Days
• Field of Search: 704/235, 704/270
• US Class Current: 704/235
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

The present invention provides a method to automate the validation of dynamic data presented over telecommunications paths. The invention utilizes continuous speaker-independent speech recognition together with a process known generally as natural language recognition to reduce dynamic utterances to machine encoded text without requiring a prior training phase. Further, when configured by the end user to do so, the test system will convert common examples of dynamic speech, such as numbers, dates, times, and currency utterances into their usual textual representation. This eliminates the limitation that all tested utterances need to be known by the test system in advance of the test. By converting the dynamic utterances to machine encoded text, the invention facilitates automated validation of the data so converted, by allowing its use as input into an automated system which can indepent source of the dynamic data and access an validate the data.

Claims

1. A method of performing speech recognition comprising the steps of:

receiving, with a test system, dynamic data from a system under test;

converting with said test system including a speech recognizer said dynamic audio data to non-audio formatted data;

comprising a textual representation format and

automatically verifying with said test system and with an independent source of said dynamic data that said non-audio formatted data is correct.

2. The method of claim 1 wherein said step of receiving comprises receiving through a telecommunications link.

3. The method of claim 2 wherein said telecommunication link is selected from the group consisting of a telephone line, a cellular telephone link, a network link and an Internet link.

4. The method of claim 1 wherein said dynamic data is selected from the group consisting of names, numbers, dates, times, and currency values.

5. The method of claim 1 wherein said textual representation comprises machine encoded text.

6. The method of claim 1 wherein said step of verifying with said test system that said non-audio formatted data is correct further comprises the step of returning a tag, said tag indicating that said non-audio formatted data was recognized.

7. The method of claim 1 wherein said step of converting with said test system said dynamic data includes the step of performing speaker independent recognition.

8. The method of claim 1 wherein said step of converting with said test system said dynamic data includes the step of performing natural language recognition.

9. A method of performing speech recognition comprising the steps of:

receiving, with a test system, including a speech recognizer audio data from a system under test, said audio data containing static data and dynamic data;

verifying with said test system that said static data is correct;

converting with said test system said dynamic data to non-audio formatted data;

comprising a textual representation format and

automatically verifying with said test system and with an independent source of said dynamic data that said non-audio formatted data is correct.

10. The method claim 9 wherein said step of receiving comprises receiving through a telecommunications link.

11. The method of claim 10 wherein said telecommunication link is selected from the group consisting of a telephone line, a cellular telephone link, a network link, and an Internet link.

12. The method in claim 9 wherein said dynamic data is selected from the group consisting of names, numbers, dates, times, and currency values.

13. The method of claim 9 wherein said textual representation comprises machine encoded text.

14. The method of claim 9 wherein said step of verifying with said test system that said non-audio formatted data is correct further comprises the step of returning a tag, said tag indicating that said non-audio formatted data was recognized.

15. The method of claim 9 wherein said step of converting with said test system said dynamic data includes the step of performing speaker independent recognition.

16. The method of claim 9 wherein said step of converting with said test system said dynamic data includes the step of performing natural language recognition.