METHOD AND APPARATUS FOR COMBINED INFORMATION FROM SPEECH SIGNALS FOR ADAPTIVE INTERACTION IN TEACHING AND TESTING

摘要

A computer system with a speech recognition componentprovides a method and apparatus for instructing and evaluating theproficiency of human users in skills that can be exhibited throughspeaking. The computer system tracks linguistic, indexical andparalinguistic characteristics of the spoken input of users, andimplements games, data access, instructional systems, and tests.The computer system combines characteristics of the spoken inputautomatically to select appropriate material and present it in amanner suitable for the user. In one embodiment, the computersystem measures the response latency and speaking rate of the userand presents its next spoken display at an appropriate speaking rate.In other embodiments, the computer system identifies the genderand native language of the user, and combines that informationwith the relative accuracy of the linguistic content of the user'sutterance to select and display material that may be easier or morechallenging for speakers with these characteristics.