Google has announced that its Voice Search product is now available in Indonesian, Malaysian, and Latin American Spanish, and it credits local users taking part in crowdsourcing for the new language availability.
Voice Search allows for someone to “Google it” by speaking into the phone rather than using the traditional method of typing-in the keywords. While plugging in the search words is fine when using a desktop, it is a more difficult and frustrating user experience to do the same on a smartphone. This is why Google launched the Voice Search product in 2008. Now, using crowdsourcing, Google has been able to launch Voice in over 20 languages.
Crowdsourcing allows Google to outsource tasks, in this case collecting voice data, to undefined groups of people through an open call of sorts. Using this method, the internet giant was able to utilize information from these users to make the product work for their specific region.
In a recent Google Mobile Blog entry, it is said, “This accomplishment could not have been possible without the help of local users in the region - really, we couldn’t have done it without them.”
International Program Manager for Google Voice Search, Linnie Ha, stated, “The traditional method of acquiring voice samples is to license the data from companies who specialize in the distribution of speech and text databases. However, from day one we knew that to build the most accurate Voice Search acoustic models possible, the best data would come from the people who would use Voice Search once it launched - our users.”
For use of the product in Latin America, Google focused on Mexican and Argentinean Spanish, which are the most different from the other accents in Central and South America.
The blog explains that, the samples collected primarily in Mexico and Argentina “were very important bookends for building a version of Voice Search that would work across the whole of Latin America.”
