Method of and system for providing adaptive respondent training in a speech recognition application
A system for conducting a telephonic speech recognition application includes an automated telephone device for making telephonic contact with a respondent and a speech recognition device which, upon the telephonic contact being made, presents the respondent with at least one introductory prompt for the respondent to reply to; receives a spoken response from the respondent; and performs a speech recognition analysis on the spoken response to determine a capability of the respondent to complete the application. If the speech recognition device, based on the spoken response to the introductory prompt, determines that the respondent is capable of competing the application, the speech recognition device presents at least one application prompt to the respondent. If the speech recognition device, based on the spoken response to the introductory prompt, determines that the respondent is not capable of completing the application, the speech recognition system presents instructions on completing the application to the respondent.
1. A method of conducting an automated, telephonic, speaker-independent speech recognition application, comprising:
making telephonic contact with a respondent;
presenting the respondent with at least one introductory speech-generated prompt requesting an audio response from the respondent to initially determine whether the respondent understands how to interact with the automated, telephonic, speaker-independent speech recognition application;
determining an interaction capability of the respondent, wherein determining an interaction capability of the respondent includes determining that a number of out-of-bounds responses, provided by the respondent, exceed a predetermined threshold;
utilizing an automated, speaker-independent speech recognition algorithm to analyze the audio response given by the respondent to the introductory speech-generated prompt; and
based on the audio response, adapting the speech recognition application to the interaction capability by;
providing branches for providing examples or practice sessions, wherein error counts are used as a variable to direct branching.
2. The method of conducting an automated, telephonic, speaker-independent speech recognition application according to claim 1 , wherein the identification includes personal identification number (PIN) of the respondent.
3. The method of conducting an automated, telephonic, speaker-independent speech recognition application according to claim 2 , further comprising, when it is determined that the respondent enters an incorrect PIN or does not know his or her PIN, automatically generating an end of call stage.
4. The method of conducting an automated, telephonic, speaker-independent speech recognition application according to claim 1 , further comprising, after the identity of the respondent is confirmed, automatically generating prompts for instructions, including sample prompts to the respondent.
5. The method of conducting an automated, telephonic, speaker-independent speech recognition application according to claim 4 , further comprising, after it is determined that the prompts for instructions are satisfactorily answered by the respondent, presenting the respondent with prompts of the application.
6. The method of conducting an automated, telephonic, speaker-independent speech recognition application according to claim 5 , further comprising, when it is determined that the respondent does not understand the process or becomes confused by the prompts, automatically providing the branches for further explanation or instructions.
7. The method of conducting an automated, telephonic, speaker-independent speech recognition application according to claim 6 , further comprising receiving feedback from the respondent including inputs regarding the application.
8. The method of conducting an automated, telephonic, speaker-independent speech recognition application according to claim 1 , wherein the automated, telephonic, speaker-independent speech recognition application automatically alters the pace or speed of verbal prompts in response to audio responses from the respondent.
9. A system for conducting an automated, telephonic speaker-independent speech recognition application, the system comprising:
an automated telephone device for making telephonic contact with a respondent; and
a speech recognition device that, upon the telephonic contact being made, is configured to:
present the respondent, when conducting the automated, telephonic speaker-independent speech recognition application, with at least one introductory prompt for the respondent to reply to;
receive a spoken response from the respondent; and
perform a speech recognition analysis on the spoken response to determine the capability of the respondent to complete the application, wherein a determined capability of the respondent is produced;
wherein the speech recognition device is configured to determine, based on (i) the speech recognition analysis on the spoken response to the introductory prompt, and (ii) the determined capability of the respondent, that respondent is capable of interacting with and completing the application, and to automatically adapt, without the need for human intervention, the automated, telephonic speaker-independent speech recognition application to the determined capability of the respondent; and
provide branches for providing examples or practice sessions, wherein error counts are used as a variable to direct branching.
10. The system for conducting an automated, telephonic, speaker-independent speech recognition application according to claim 9 , wherein the identification includes personal identification number (PIN) of the respondent.
11. The system for conducting an automated, telephonic, speaker-independent speech recognition application according to claim 10 , wherein the speech recognition device is further configured to, when it is determined that the respondent enters an incorrect PIN or does not know his or her PIN, automatically generate an end of call stage.
12. The system for conducting an automated, telephonic, speaker-independent speech recognition application according to claim 9 , wherein the speech recognition device is further configured to, after the identity of the respondent is confirmed, automatically generate prompts for instructions, including sample prompts to the respondent.
13. The system for conducting an automated, telephonic, speaker-independent speech recognition application according to claim 12 , wherein the speech recognition device is further configured to, after determining that the prompts for instructions are satisfactorily answered by the respondent, present the respondent with prompts of the application.
14. The system for conducting an automated, telephonic, speaker-independent speech recognition application according to claim 13 , wherein the speech recognition device is further configured to, after determining that the respondent does not understand the process or becomes confused by the prompts of the application, automatically provide the respondent with the branches for further explanation or instructions.
15. The system for conducting an automated, telephonic, speaker-independent speech recognition application according to claim 14 , wherein the speech recognition device is further configured to receive feedback from the respondent including feedback on the application.
16. The system for conducting an automated, telephonic, speaker-independent speech recognition application according to claim 9 , wherein the speech recognition device is further configured to, in response to audio responses from the respondent, automatically change the pace or speed of verbal prompts provided to the respondent.