Importance

Loading Importance Indicators...

Abstract

A real-time speech-based learning/training system distributed between client and server, and incorporating speech recognition and linguistic processing for recognizing a spoken question and to provide an answer to the student in a learning or training environment implemented on an intranet or over the Internet, is disclosed. The system accepts the student's question in the form of speech at his or her computer, PDA or workstation where minimal processing extracts a sufficient number of acoustic speech vectors representing the utterance. The system as implemented accepts environmental variables such as course, chapter, section as selected by the user so that the search time, accuracy and response time for the question can be optimized. A minimum set of acoustic vectors extracted at the client are then sent via a communications channel to the server where additional acoustic vectors are derived. Using Hidden Markov Models (HMMs), and appropriate grammars and dictionaries conditioned by the course, chapter and section selections made by the student, the speech representing the user's query is fully decoding to text at the server. This text corresponding to the user's query is then simultaneously sent to a natural language engine and a database processor where an optimized SQL statement is constructed for a full-text search from a SQL database for a recordset of several stored questions that best matches the user's query. Further processing in the natural language engine narrows the search down to a single stored question. The answer that is paired to this single stored question is then retrieved from the file path and sent to the student computer in compressed form. At the student's computer, the answer is articulated using a text-to-speech engine in his or her native natural language. The system requires no training and can operate in several natural languages.

Loading the Abstract Image...

First Claim