14 DAY TRIAL // Launched two years ago, Google's Voice Search function is now getting improved, as Google has just announced the release the “Personalized recognition” feature. The company claims that the new feature will greatly improve the accuracy of its speech recognition service.
Google sees the voice search function on mobile device as an important part of its business.
According to the company, one in four searches on Android smartphone is done using the Voice Search application, while the search volume on Android devices has increased 50% in the last six months.
“When we launched Voice Search more than two years ago, we wanted it to “just work” right out of the box, without an initial setup process," said Amir Mane, Product Manager. Google.
"But we always knew we could build a more accurate model by listening to your voice, and learning how you, as a unique individual, speak. So today we’re launching personalized recognition,” added Mane.
Personalized recognition provides users with more accurate results when the voice search function is used, as the new service gradually learns the patterns of a person’s speech.
Google stores recordings of words users ask to be recognized within their Google account. The company then uses these recordings to build a speech pattern specifically for the user.
At the moment, the newly launched Personalized recognition feature is only available for the English language in the United States, but Google plans to extend the support to other countries and languages in the near future.
The feature is compatible with smartphones running Android 2.2 or higher. Users who wish to benefit from the Personalized recognition function have to download the latest version of Voice Search from the Android Market.
According to Google, the new application also includes “several improvements to name recognition and speed, especially over 3G and EDGE connections.”
