Word of Mouth: Introducing Voice Search for Indonesian, Malaysian and Latin American Spanish

Wednesday, March 30, 2011 | 9:36 AM

(Read more about the launch of Voice Search in Latin American Spanish on the Google América Latina blog)

Today we are excited to announce the launch of Voice Search in Indonesian, Malaysian, and Latin American Spanish, making Voice Search available in over two dozen languages and accents since our first launch 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. Let me explain:

In 2010 we launched Voice Search in Dutch, the first language where we used the “word of mouth” project, a crowd-sourcing effort to collect 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. 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.

Since then, in each country, we found small groups of people who were avid fans of Google products and were part of a large social network, either in local communities or on online. We gave them phones and asked them to get voice samples from their friends and family. Everyone was required to sign a consent form and all voice samples were anonymized. When possible, they also helped to test early versions of Voice Search as the product got closer to launch.

Building a speech recognizer is not just limited to localizing the user interface. We require thousands of hours of raw data to capture regional accents and idiomatic speech in all sorts of recording environments to mimic daily life use cases. For instance, when developing Voice Search for Latin American Spanish, we paid particular attention to Mexican and Argentinean Spanish. These two accents are more different from one another than any other pair of widely-used accents in all of 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.

As an International Program Manager at Google, I have been fortunate enough to travel around the world and meet many of our local Google users. They often have great suggestions for the products that they love, and word of mouth was created with the vision that our users could participate in developing the product. These Voice Search launches would not have been possible without the help of our users, and we’re excited to be able to work together on the product development with the people who will ultimately use our products.

22 comments:

Vincent said...

Ok now bring Canadian French !
thanks

Unknown said...

+1

Français Canada!

kefthim said...

Any chance of getting Greek voice support for android anytime soon???

Unknown said...

It'll be good if your voice recognition engine could understand mixed languages too.
For example, I have default language settings in my phone as 'English', but sometime I'd like to speak in 'Russian'. Now I have to switch language settings first, what is very useless.

Anyway thank you for you job, it's awesome! ;-)

Awet said...

ARABIC please

David H. said...

Austrian German would be nice.

Apart from that, the voice input should have options to override the input an app configures.

i.e. if an app expects es-es, it should be possible to tell android to use es-ar for any es-* input.
So far I can only configure a default input, but some apps (dictionaries, translators) switch to their own settings and they hardly ever allow choosing between the dialects. Or just let me tell the system which languages I can write and which languages I can speak and it selects the appropriate settings for me, something like that.

Ruben said...

Still waiting for Portuguese... Next time maybe...

Unknown said...

Viva la vida

Stellar Drift said...

Don't go for number of people, go for money - chose the Danish they are rich ;)

Unknown said...

This is a excellent news, but aside from natural language search, where can we find the list of voice shortcuts for Google Search in French or Spanish.

The list in English is available but I have been unable to locate the lists in other languages.

Thank you

Aran Chandran said...

Linne, the language is Malay, not Malaysian. Malaysian is used for the people only. Terima kasih, sekarang saya dapat mengunakan voice search dalam Bahasa Melayu.

Mufid said...

Keren. Berarti dia sudah bisa mengenali bahasa semacam ini dengan suara yah? Good job, Google.

Kien said...

As a Malaysian, this is very exciting. May I inquire whether by "Malaysian", you mean the Malay language (i.e., Bahasa Malaysia), or English spoken with a Malaysian accent. (It's very close to "Singlish" or Singapore English.) Personally, I tend to avoid using voice activated commands because I assume they do not recognise English spoken in my accent.

mcrosmar said...

What about Greek?

Thanks...

Sergio Romano said...

Great. Perfecto!
Thanks Google. I've tried it and it's perfect.

Is this working with Voice Actions too?

Anonymous said...

@Kien By "Malaysian" we mean the Malay language (Bahasa Malaysia).

Anonymous said...

@sexaybeast The name of the official language of Malaysia changed a couple of times in the past. Currently the preferred term seems to be "Bahasa Malaysia". See for example http://ms.wikipedia.org/wiki/Bahasa_Malaysia and http://penerangan.kpkk.gov.my/index.php?option=com_content&task=view&id=1196&Itemid=2

David H. said...

Well, congrats to the team that optimized the Argentine Spanish input. I have a pretty funny situation now: My native language is german, nevertheless Google Maps never gets what I say when I set the input to German. If I set it to Argentine Spanish and start searching adresses in Argentina it understands me almost perfectly eventhough I have a strong accent.
Do some work on the German language please!

CyberZone said...

Terima kasih banyak, Google....
Teruskan karya-karya terbaikmu...!

Afriza N. Arief said...

Please add this Indonesian to Android keyboard!

The Voice Search is very good and pretty accurate indeed but I cannot compose SMS/email using voice yet.

a.wirayudha said...

Terima kasih Google! Your innovation will inspire us to live better.

Oluwaseun Obajobi said...

Yoruba language please :)