Evaluating prosodic cues as a means to disambiguate algebraic expressions: an empirical study

Document Type

Conference Proceeding

Department or Administrative Unit

Computer Science

Publication Date



The automatic translation of written mathematical expressions to their spoken equivalent is a difficult task. Written mathematics makes use of specialized symbols and a 2-dimensional layout that is hard to translate into clear and unambiguous spoken words. Our approach is to use prosody to help listeners follow along to mathematical expressions spoken aloud with text-to-speech synthesized voices. To achieve this, we developed and empirically tested XSL transformation rules that automatically translate mathematical expressions marked-up with Presentation MathML into corresponding markup using the Speech Synthesis Markup Language (SSML). In this paper, we report on the results from an empirical study we conducted that showed that the simple insertion of pauses inside spoken mathematical expressions dramatically improved subjects' ability to disambiguate between two similar algebraic expressions. Result from our study should benefit designers of screen readers and related audio-based tools that produce spoken renderings of mathematical expressions.


This article was originally published in . The full-text article from the publisher can be found here.

Due to copyright restrictions, this article is not available for free download from ScholarWorks @ CWU.


Assets '09: Proceedings of the 11th international ACM SIGACCESS conference on Computers and accessibility


Copyright 2009 ACM