Using Automatic Speech Recognition to Dictate Mathematical Expressions: The Development of the 'TalkMaths' Application at Kingston University

摘要

Speech technology - especially automatic speech recognition - has now advanced to a level where it can be of great benefit both to able-bodied people and those with various disabilities. In this article we describe an application "TalkMaths" which, using the output from a commonly-used conventional automatic speech recognition system, enables the user to dictate mathematical expressions in a relatively straightforward way. These then get converted into electronic formats, so that they can be embedded in a document and/or displayed in an editor or web browser. This process can be used for preparing teaching material, assignments, or entering mathematical content for online tests. Our system does not require the user to have extensive knowledge of the syntax of any markup language or mathematical document specification language, so that learning to use it should be relatively straightforward for non-specialists. The way in which our system analyses, converts and encodes the spoken mathematical expressions is a novel approach.