Applications in Accessibility of Text-to-Speech Synthesis for South African Languages: Initial System Integration and User Engagement Georg I. Schlünz Human Language Technology Research Group CSIR Meraka Institute Pretoria, South Africa gschlunz@csir.co.za Ilana Wilken Human Language Technology Research Group CSIR Meraka Institute Pretoria, South Africa iwilken@csir.co.za Carmen Moors Human Language Technology Research Group CSIR Meraka Institute Pretoria, South Africa cmoors@csir.co.za Tebogo Gumede Human Language Technology Research Group CSIR Meraka Institute Pretoria, South Africa tgumede@csir.co.za Willem van der Walt Human Language Technology Research Group CSIR Meraka Institute Pretoria, South Africa wvdwalt@csir.co.za Karen Calteaux Human Language Technology Research Group CSIR Meraka Institute Pretoria, South Africa kcalteaux@csir.co.za Kerstin Tönsing Centre for Augmentative and Alternative Communication University of Pretoria Pretoria, South Africa kerstin.tonsing@up.ac.za Karin van Niekerk Centre for Augmentative and Alternative Communication University of Pretoria Pretoria, South Africa karin.vanniekerk@up.ac.za ABSTRACT Persons with certain disabilities face barriers to information access and interpersonal communication. Assistive technologies provide workaround solutions to these problems. Augmentative and al- ternative communication systems aid the person with little or no functional speech to speak out loud. Screen readers and accessible e-books allow a print-disabled (visually-impaired, partially-sighted or dyslexic) individual to read text material by listening to audio versions. Text-to-speech synthesis converts electronic text into arti- fcial speech and is used as the vocalisation component in the assis- tive technologies. For these three use cases, we report on an initial round of system integration and user engagement of the Qfrency text-to-speech voices that provide access to synthetic speech in the South African languages. Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for proft or commercial advantage and that copies bear this notice and the full citation on the frst page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specifc permission and/or a fee. Request permissions from permissions@acm.org. SAICSIT ’17, September 26–28, 2017, Thaba Nchu, South Africa © 2017 Copyright held by the owner/author(s). Publication rights licensed to Associa- tion for Computing Machinery. ACM ISBN 978-1-4503-5250-5/17/09. . . $15.00 https://doi.org/10.1145/3129416.3129445 CCS CONCEPTS · Human-centered computing → Sound-based input / out- put; Empirical studies in accessibility; Accessibility technolo- gies; KEYWORDS Accessibility, assistive technology, text-to-speech, South African languages, system integration, user engagement ACM Reference format: Georg I. Schlünz, Ilana Wilken, Carmen Moors, Tebogo Gumede, Willem van der Walt, Karen Calteaux, Kerstin Tönsing, and Karin van Niekerk. 2017. Applications in Accessibility of Text-to-Speech Synthesis for South African Languages: Initial System Integration and User Engagement. In Proceedings of SAICSIT ’17, Thaba Nchu, South Africa, September 26–28, 2017, 10 pages. https://doi.org/10.1145/3129416.3129445 1 INTRODUCTION Interpersonal communication is a fundamental part of our daily human lives. We need to communicate with one another when we want to speak our hearts and minds, not only to be heard but also to be understood. We use diferent channels to convey our messages, including verbal speech, written text, and drawn images. We alternate between the roles of the speaker (writer, artist) and listener (reader, interpreter). During our turn-taking, we refect on what each party has said (written, drawn) and we adjust our interaction to accommodate the other party in order to reach a mutual understanding.