Development of an algorithm for improving quality and information processing capacity of MathSpeak synthetic speech renderings

Abstract

Purpose. MathSpeak is a set of rules for non speaking of mathematical expressions. These rules have been incorporated into a computerised module that translates printed mathematics into the non-ambiguous MathSpeak form for synthetic speech rendering. Differences between individual utterances produced with the translator module are difficult to discern because of insufficient pausing between utterances; hence, the purpose of this study was to develop an algorithm for improving the synthetic speech rendering of MathSpeak.

Method. To improve synthetic speech renderings, an algorithm for inserting pauses was developed based upon recordings of middle and high school math teachers speaking mathematic expressions. Efficacy testing of this algorithm was conducted with college students without disabilities and high school/college students with visual impairments. Parameters measured included reception accuracy, short-term memory retention, MathSpeak processing capacity and various rankings concerning the quality of synthetic speech renderings.

Results. All parameters measured showed statistically significant improvements when the algorithm was used.

Conclusion. The algorithm improves the quality and information processing capacity of synthetic speech renderings of MathSpeak. This increases the capacity of individuals with print disabilities to perform mathematical activities and to successfully fulfill science, technology, engineering and mathematics academic and career objectives.

Keywords:

• Blindness
• visual impairment
• mathematics
• MathSpeak
• synthetic speech

Acknowledgements

The authors thank Dave Schleppenbach, Dennis Leas, Waseem Sheikh (key gh personnel) and the Purdue AAC Research Group, especially Soo Jung Chae (doctoral student), Jeremy Gallagher (undergraduate assistant), Emily Metzer (undergraduate research trainee). The research was sponsored by NSF STTR Grant IIP-0712199 awarded to gh LLC and Purdue University. gh LLC is a privately owned company operating out of Purdue's Research Park. The contents do not necessarily represent the policy of NSF and endorsement by the federal government is not to be assumed.