Method of and system for providing adaptive respondent training in a speech recognition application

摘要

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.

主权项

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.