Google is helping mobile phones to understand the intricate nuances in your voice so you can start searching the internet more accurately - without using your fingers.

On December 14 the internet giant introduced personalized voice recognition, taking its existing Vocal Search application one step further.

The company originally launched Voice Search over two years ago. The hands-free service lets people speak the search terms they are looking for instead of tapping them into the phone's search engine.

While Vocal Search has helped many users find the things they were looking for over the years, there have often been times when the translations were not as accurate as they could be.

"[W]e built speech models broad enough to accommodate a wide variety of people, regardless of gender, age, and accents, or variations in pitch, pace, and other factors," says 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."

On first running the updated Voice Search application, Android users are given the option to opt into personalized voice recognition, effectively enabling their device to "learn" how to recognize and understand the unique accent and speech patterns in their voice.

As soon as users decide to opt into the service, Google starts building a speech model that is unique to them, linking their personal speech model to their Google Account.

"Although subtle, accuracy improvements begin fairly quickly and will build over time," says Google.

The personalized recognition feature within Voice Search is currently only available for people living in the US with an Android device running OS 2.2 or higher. Other languages and countries are expected to be included in the near future.

The updated Voice Search app can be downloaded from Google's Android Market.