Back in 2001, Wikipedia was launched by Jimmy Wales and Larry Sanger as a free, Internet encyclopedia for the masses. Over the following 15 years, Wikipedia has grown in popularity to become one of the ten most popular websites with some 38 million articles available in over 290 languages.
Despite amassing a formidable amount of reference content, there has still been a hurdle for those with visual impairments, illiteracy, or learning disabilities.
In recognition of this challenge, Wikimedia Sweden has teamed up with the KTH Royal Institute of Technology to build a new speech synthesis platform with optimizations specific to Wikipedia. The initiative, which aims to deliver by September 2017, will only target a few specific languages. KTH Professor Joakim Gustafson said:
“Initially, our focus will be on the Swedish language, where we will make use of our own language resources. Then we will do a basic English voice, which we expect to be quite good, given the large amount of open source linguistic resources. And finally, we will do a rudimentary Arabic voice that will be more a proof of concept.”
In the spirit of the free and open nature of Wikipedia, the new speech synthesis platform will also be made open source, similar to the MediaWiki software already offered. It is also expected that the software could leverage the platform for uses other than reading wiki pages.
While accessibility features in operating systems have continued to mature across the various form factors, content accessibility and interaction hasn't necessarily kept up. According to Wikimedia Sweden, 25 percent of Wikipedia users, or approximately 125 million a month, require or prefer the use of spoken text, underscoring the importance of this initiative.