Development and Initial Evaluation of the ClearSpeak Style for Automated Speaking of Algebra

Abstract

Since its 1947 founding, ETS has conducted and disseminated scientific research to support its products and services, and to advance the measurement and education fields. In keeping with these goals, ETS is committed to making its research freely available to the professional community and to the general public. Published accounts of ETS research, including papers in the ETS Research Report series, undergo a formal peer-review process by ETS staff to ensure that they meet established scientific and professional standards. All such ETS-conducted peer reviews are in addition to any reviews that outside organizations may provide as part of their own publication processes. Peer review notwithstanding, the positions expressed in the ETS Research Report series and other published accounts of ETS research are those of the authors and not necessarily those of the Officers and Trustees of Educational Testing Service.The Daniel Eignor Editorship is named in honor of Dr. Daniel R. Eignor, who from 2001 until 2011 served the Research and Development division as Editor for the ETS Research Report series. The Eignor Editorship has been created to recognize the pivotal leadership role that Dr. Eignor played in the research publication process at ETS. The work described in this report is the first phase of a project to provide easy-to-use tools for authoring and rendering secondary-school algebra-level math expressions in synthesized speech that is useful for students with blindness or low vision. This report describes the initial development, software implementation, and evaluation of the ClearSpeak speech style-implemented for initial testing purposes using prerecorded synthetic speech, and implemented later in the project as a collection of predefined rules and in some cases variations (called preferences in ClearSpeak)-for automatically generated synthetic speech. In addition to wording, speech styles can specify pausing (or other prosodic cues) within the speech. The ClearSpeak style focuses on speech for secondary school algebra. The evaluation compares a prototype of the ClearSpeak style to two pre-existing speech styles: MathSpeak and SimpleSpeak. The primary parameters evaluated are students' success in drawing conclusions about the content and structure of math expressions and their perceptions regarding the familiarity, helpfulness, and understandability of the expressions as spoken. Please see Appendix E for information on obtaining a version of this report that is fully accessible using the tools described. ETS Research Report Series ISSN 2330-8516 R E S E A R C H R E P O R T Development and Initial Evaluation of the ClearSpeak Style for Automated Speaking of AlgebraKeywords math; accessibility; blindness; visual impairment; text-to-speech; MathML; algebra; STEM; ClearSpeak; assistive technology; screen reader doi:10. 1002/ets2.12103 There is a great need to improve mathematics achievement in students with visual impairments (SVIs), for whom there is a large achievement gap compared to students without disabilit...

Expanding Audio Access to Mathematics Expressions by Students With Visual Impairments via MathML

“…Discussions with stakeholders, and, as noted previously, our previous work (see Frankel et al, , and Frankel & Brownstein, ), and information in the literature (see, e.g., Bates & Fitzpatrick, ; Ferreira & Freitas, ) strongly confirmed our belief in the importance of interactive navigation for math expressions; accordingly, building that functionality was an important part of this project. This section briefly describes the navigation tools developed, all of which are controlled via keystrokes.…”

“…As discussed in more detail elsewhere (Frankel et al, ), spoken math in MathPlayer is generated from the underlying MathML encoding using a combination of rules , preferences , and exact speech . Rules are default ways of speaking math structures.…”

“…We previously reported on the development and results of our initial studies with SVIs of the ClearSpeak style for synthetic speech of math expressions commonly encountered in high school algebra (Frankel et al, ) and on the usefulness and suitability for inclusion in ClearSpeak of certain enhanced prosodic and lexical cues (Frankel & Brownstein, ). In the first report, we described advantages found for ClearSpeak over two pre‐existing synthetic speech styles (MathSpeak and SimpleSpeak).…”

An Evaluation of the Usefulness of Prosodic and Lexical Cues for Understanding Synthesized Speech of Mathematics

“…Until our project and others with similar goals 1 leveraged the MathML markup language, these challenges had prevented screen readers from providing meaningful access to mathematical expressions. These issues are discussed in more detail in our previous report (Frankel, Brownstein, Soiffer, & Hansen, 2016).…”

Rule based intelligent system verbalizing mathematical notation

“…The respective WER and BLEU metrics for the quality of translation performed in each case in comparison to the assumed natural language transcription(s) of the exemplary formulae (referred to as Spoken English) were calculated in each case. The assumed verbalization are based on own elaboration and literature sources, including fundamental book [11], as well as some academic reports [19,22,37] and textbooks [47].…”