Speech recognition assisted data entry system and method

• US 6,510,414 B1
• Filed: 10/05/1999
• Issued: 01/21/2003
• Est. Priority Date: 10/05/1999
• Status: Expired due to Term

• Current Assignee: Cisco Technology, Inc. (Cisco Systems, Inc.)
• Original Assignee: Cisco Technology, Inc. (Cisco Systems, Inc.)
• Inventors: Chaves, Gerardo
• Primary Examiner(s): MCFADDEN, SUSAN IRIS
• Application Number:
  US09/412,891
• Time in Patent Office: 1,204 Days
• Field of Search: 704/270, 704/275, 704/270.1, 379/88.01, 379/218, 379/219, 379/221, 379/430, 379/93.23, 379/93.34, 370/352
• US Class Current: 704/270
• CPC Class Codes: G10L 15/18 using natural language modelling
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: H04M 2201/40 using speech recognition speech recognition per se G10L15/00
• CPC Class Codes: H04M 2201/60 Medium conversion
• CPC Class Codes: H04M 3/51 Centralised call answering arrangements requiring operator intervention , e.g. call or contact centers for telemarketing

Abstract

A speech recognition assisted data entry system includes a computing system and a speech recognition application operable to run on the computing system. The speech recognition application is operable to receive data from a caller and convert the data to recognizable characters. The system also includes a converted cache operable to store the recognizable characters. The system further includes a set of recognition rules operable to be applied to the recognizable characters in the converted cache to automatically determine the recognizable characters corresponding to a data entry field of a data entry application.

Claims

1. A speech recognition assisted data entry system comprising:

a speech recognition system comprising a speech recognition application operable to be activated by a call center agent, the activated speech recognition application operable to receive data from a caller and convert the data to recognizable characters;

a converted cache operable to store the recognizable characters;

a set of recognition rules operable to be applied by the speech recognition system to the recognizable characters in the converted cache to automatically determine the recognizable characters corresponding to a data entry field of a data entry application; and

a control system operable to;

receive a first selection of a first data entry field from the call center agent;

direct the speech recognition application to capture a first set of recognizable characters corresponding to the first data entry field in response to the first selection;

receive a second selection of a second data entry field from the call center agent; and

direct the speech recognition application to capture a second set of recognizable characters corresponding to the second data entry field in response to the second selection.

2. The system of claim 1, wherein the speech recognition assisted data entry system further comprises an input system accessible by the call center agent to input the recognizable characters corresponding to the data entry field into the data entry application.

3. The system of claim 2, wherein the speech recognition system is further operable to indicate to the call center agent the recognizable characters corresponding to the data entry field.

4. The system of claim 1, further comprising an output system operable to output the data received from the caller to an output device.

5. The system of claim 4, wherein the output device comprises a speaker operable to output audio signals of the data received from the caller.

6. The system of claim 1, wherein the speech recognition system is further operable to automatically input the recognizable characters corresponding to the data entry field into the data entry application.

7. The system of claim 1, wherein the speech recognition assisted data entry system further comprises a voice file, and is further operable to convert the voice file to an audio signal and transmit the audio signal to the caller.

8. The system of claim 1, wherein the speech recognition system is further operable to convert the characters corresponding to the data entry field to an audio signal and transmit the audio signal to the caller.

9. The system of claim 8, wherein the speech recognition assisted data entry system further comprises a voice file, and is further operable to convert the voice file to an audio signal, and to combine the audio signal of the voice file with the audio file of the characters corresponding to the data entry field and transmit the combined audio files to the caller.

10. A method for speech recognition assisted data entry comprising:

initiating a communication connection between a caller and a call center agent;

activating a speech recognition application in response to a request from the call center agent;

receiving data from the caller via the communication connection;

converting the data to recognizable characters using the speech recognition application;

storing the recognizable characters in a converted cache;

applying a set of recognition rules to the recognizable characters stored in the converted cache to automatically determine the recognizable characters corresponding to one or more data entry fields of a data entry application;

indicating to the call center agent the recognizable characters that correspond to the one or more data entry fields;

receiving one or more data confirmations from the call center agent; and

entering the recognizable characters that correspond to the data entry fields into one or more of the data entry fields in response to the one or more data confirmations from the call center agent.

11. The method of claim 10, wherein the step of entering comprises automatically entering the recognizable characters corresponding to the data entry field in the data entry application.

12. The method of claim 10, further comprising:

retrieving a recorded voice file;

converting the voice file to an audio signal; and

transmitting the audio signal to the caller.

13. The method of claim 12, further comprising:

converting the characters corresponding to the data entry field to an audio signal;

combining the audio signal of the characters corresponding to the data entry field with the audio signal of the voice file; and

transmitting the combined audio signals to the caller.

14. The method of claim 10, further comprising:

indicating the recognizable characters corresponding to the data entry field; and

receiving input from the call center agent to input the recognizable characters corresponding to the data entry field into the data entry application.

15. The method of claim 10, wherein the steps of the method are performed by logic embodied in a computer readable medium.

21. The method of claim 15, wherein the steps of the method are performed by logic embodied in a computer readable medium.

16. A method for speech recognition assisted data entry comprising:

establishing a communication connection between a caller and a call center agent;

designating a first data entry field selected by the call center agent in a data entry application;

activating a speech recognition application in response to the selection of the first data entry field;

receiving first data from the caller;

converting the first data to recognizable characters using the speech recognition application in the first data entry field of the data entry application;

after the data is converted, designating a second data entry field selected by the call center agent;

receiving second data from the caller; and

converting the second data to recognizable characters using the speech recognition application in the second data entry field of the data entry application.

17. The method of claim 16, further comprising:

retrieving a recorded voice file;

converting the voice file to an audio signal; and

transmitting the audio signal to the caller.

18. The method of claim 17, further comprising transmitting the combined audio signal to a speaker accessible by the call center agent.

19. The method of claim 18, further comprising transmitting the combined audio signal to a speaker accessible by a call center agent.

20. The method of claim 16, further comprising:

retrieving a recorded voice file;

converting the voice file to an audio signal; and

transmitting the audio signal to the caller.

22. A system for speech recognition assisted data entry, comprising:

means for initiating a communication connection between a caller and a call center agent;

means for activating a speech recognition application in response to a request from the call center agent;

means for receiving data from the caller via the communication connection;

means for converting the data to recognizable characters using the speech recognition application;

means for storing the recognizable characters in a converted cache;

means for applying a set of recognition rules to the recognizable characters stored in the converted cache to automatically determine the recognizable characters corresponding to a data entry field of a data entry application;

means for indicating to the call center agent the recognizable characters that correspond to the one or more data entry fields;

means for receiving one or more data confirmations from the call center agent; and

means for entering the recognizable characters that correspond to the data entry fields into one or more of the data entry fields in response to the one or more confirmations from the call center agent.

23. A method for speech recognition assisted data entry, comprising:

initiating a communication connection between a caller and a call center agent;

activating a speech recognition application in response to a request from the call center agent;

receiving data from the caller via the communication connection;

converting the data into recognizable characters using a speech recognition application;

applying a set of recognition rules to the data to identify recognizable characters corresponding to one or more data entry fields of a data entry application, the recognition rules comprising;

a first rule for determining the data entry field corresponding to numerical data based on a count of numerals in the numerical data;

a second rule for determining the recognizable characters of a first corresponding data entry field based on a second corresponding data entry using a nested table, the nested table providing a plurality of first entries and a plurality of second entries, each second entry corresponding to a subset of the first entries; and

a dictionary for identifying words associated with data entry fields of the data entry application that receive the words; and

based on application of the recognition rules, entering the recognizable characters into one or more of the data entry fields.