Nuance enhances mobile speech recognition

Advanced speech recognition to improve the usability of mobile devices

Nuance Communications has launched a system that will improve the text-to-speech and speech recognition abilities of mobile devices.

The product, Nuance Mobile Speech Platform, is expected to provide end-users with a simple, intuitive user interface, and allow mobile application developers to enhance their offerings.

Nuance is the same company that produces Dragon NaturallySpeaking.

The Nuance Mobile Speech Platform is built on a client-server architecture, which enables advanced speech recognition functions and any other queries to be sent from the mobile device to a remote server. As a server typically has much more processing power than a mobile device would, the platform is able to handle a much larger speech recognition vocabulary along with performing other tasks.

"Speech recognition is not limited to the device - it is sent over a packet to the server," explained Peter Chidiac, regional director of Nuance Asia Pacific and Japan's speech division,. "That then enables the server to be connected to the Internet, to corporate email, to SMS servers and so on, to enable mobile dictation with virtually unconstrained recognition."

Through the platform, end users will be able to perform searches, dictate emails and SMS messages, and have any incoming emails and messages read out to them, which, Chidiac expects, will improve the usability and efficiency of mobile devices.

To enable 'natural language processing', Nuance's speech recognition technology analyses a collection of utterances from local call centre data in Australia, the US, and the UK. Using statistical and semantic language modeling, the system compares the data against what is said, to decide on the most probable function the user is trying to perform.

"It's semi-artificial intelligence," Chidiac said. "You can say exactly what you want, and the system will route you to the right area, or the right person and so on. You don't have to go through the various prompts."

Using the platform, he said, a location search that would normally need around 47 clicks on a standard keypad could be performed with only two clicks and some verbal commands.

"What it enables is for you to get to what you want and access content, information, and do your communications in a more natural and faster way," Chidiac said.

Nuance is currently in discussions with enterprises and telecommunications carriers to bring the mobile platform to end-users. While Chidiac hopes the technology will reach the market by 2007, he said its commercial launch will be largely dependent on the company that deploys it.

Join the newsletter!

Error: Please check your email address.

More about NuanceNuance Communications Australia

Show Comments

Market Place