Wikimedia Foundation and Sweden’s KTH Royal Institute of Technology have partnered together to enable crowdsourced speech engine for Wikipedia. This new development will let you start talking to the online encyclopedia by as early as 2017.
The new engine will be the world’s first crowdsourced speech synthesis platform that will be specifically optimised for Wikipedia. However, it will be available as an open source offering for the masses and will work with any websites that use the MediaWiki software.
“Initially our focus will be on Swedish language, where we will make use of our own language resources,” KTH speech technology professor Joakim Gustafson says in a statement. “Then we will do a basic English voice, which we expect to be quite good given the large amount of open source linguistic resources.”
Apart from Swedish and English, there are plans to add Arabic voice to the new platform. Separate speech engines in these three languages will be ready in September 2017. Moreover, the initial development is expected to encourage users to extend synthesised speech to the remaining 280 languages in which Wikipedia is currently available.
The material available through the speech engine will be freely licensed. It will come under the rules of Wikimedia Commons to let anyone could use the given content.
The speech engine will help people with reading difficulties or visual impairment. Wikipedia estimates that 25 percent of its total user base — nearly 125 million monthly users — will benefit from the new development. Additionally, it would power some other online sites to deliver an advanced experience.