Would you like to help the web do a better job pronouncing content for users who rely on text to speech (TTS)?
All persons interested in making TTS more effective on the web are cordially invited to join the newly created Pronunciation Task Force in the accessible Platform Architectures (APA) Working Group.
Correct pronunciation is not just a nice to have for users who rely on TTS. There are situations where it’s mandatory if the web is to function as an equal opportunity environment. Anyone taking a timed test, for example, should not be diverted and slowed down by improperly pronounced content. APA believes there is already sufficient core technology available in existing W3C recommendations to create cross-platform functional guidance for content authors interested in correct pronunciation through TTS. The task of the Pronunciation Task Force is to identify and specify the optimal approach which can deliver reliably accurate pronunciation across browser and operating environments.
The educational publishing and educational assessment communities have long been aware of the negative impact of unreliable TTS pronunciation. Mismatches between how content is spoken by TTS and how it should be spoken according to pedagogical practice are well known to confuse and otherwise hamper the student experience.
As defined in its Work Statement the Pronunciation Task Force will publish three documents in furtherance of this goal:
- A Gap Analysis;
- A Use cases and requirements document;
- A document proposing a technical approach for providing the solution to address the need for accurate pronunciation and presentation of spoken content various languages.
The APA Spoken Presentation Task Force was formed in October 2018 and is now recruiting participants from across the spectrum of content publishers, accessibility standards, assistive technology, and speech technologies interested in solving this challenge. While the impact of any solution will be significant for the education community, we believe there will be broader benefit as spoken presentation grows as a modality for interaction with the web. The planned work of the task force is described in the work statement and task force home page.
This effort continues work begun in the IMS Global Learning Consortium (GLC), and there is background information on work conducted prior to the formation of the Task Force by ETS in a SSML in HTML Proposal and SSML required for Educational Assessments and details on the IMS GLC QTI 2.2 inclusion of SSML.
To join the Pronunciation Task Force please contact:
Michael Cooper, APA Staff Contact.
Questions about the work of the Task Force may be directed to:
Irfan Ali, Pronunciation Task Force Facilitator.