Google Voice Search in Indonesian, Malaysian, and Latin American Spanish

By on March 31st, 2011 07:59 GMT

Mountain View-based Internet giant Google has just announced the launch of Voice Search in new languages, namely Indonesian, Malaysian, and Latin American Spanish.

With this launch, Voice Search becomes available in over two dozen languages and accents, since it was initially launched in November 2008.

“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,” the company notes in a recent post on the Google Mobile Blog.

Linne Ha, International Program Manager, Google Voice Search notes that the new launch was based on the “word of mouth” project, which is nothing more than a crowd-sourcing effort aimed at collecting the most accurate voice data possible.

“The traditional method of acquiring voice samples is to license the data from companies who specialize in the distribution of speech and text databases,” Linne Ha explains.

“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.”

In each country, they found groups of people fond of Google's products, gave them phones, and asked for voice samples from their friends and family. All samples were anonymized, and each participant was required to sign a consent form.

With Voice Search for Latin American Spanish, the company was focused on Mexican and Argentinean Spanish, which are more different that all other accents in South and Central America.

“Samples collected in these countries were very important bookends for building a version of Voice Search that would work across the whole of Latin America. We also chose key countries such as Peru, Chile, Costa Rica, Panama and Colombia to bridge the divergent accent varieties,” the blog post explains.

The bottom line is that the launch of Voice Search in newer languages was not possible without the help of users, who contributed not only with voice samples, but with their own ideas as well.

Comments