Thursday, 24 October 2013

A chat with machines



Voice-command interfaces are now almost pervasive in most electronic devices, from mobile phones, TVs, even automobiles. The concept of holding a conversation with a computer seemed pure science fiction until recently.

But things are changing, and quickly. A growing number of people now talk to their mobile smart phones, asking them to send e-mail and text messages, search for directions, or find information on the Web.

Now the rapid rise of powerful mobile devices is making voice interfaces even more useful and pervasive. Current smart phones pack as much processing power as the laboratory machines he worked with used in the '90s.

Smart phones also have high-bandwidth data connections to the cloud, where servers can do the heavy lifting involved with both voice recognition and understanding spoken queries.

"The blend of more data and extra computing power has put at our disposal infinite possibilities,” says Mr Josep Kim, the Managing Director LG East Africa. Speech has increasingly proven supremely suited for mobile computing partly because users have their hands and eyes occupied; but also because a single spoken command can accomplish tasks that would normally require a multitude of swipes and presses.

The last few years have seen hype around voice commands reached the peak of inflated expectations with the buzz around Apple's Siri, only to recede straight after. The new wave of voice-enabled devices showcased at IFA 2013 earlier in September offers a glimpse of how voice commands may make consumer's lives easier.

Siri, the voice-activated personal assistant built into the iPhone, was at one time the most prominent example of a mobile voice interface. But voice functionality is built into Android, the Windows Phone platform, and most other mobile systems, as well as many apps. While these interfaces still have considerable limitations, we are inching closer to machine interfaces we can actually talk to.

However the jury is still out, with consumer adoption the bellwether for technological success. “The development of the Werniche Project has seen LG make quick progress in incorporating voice commands. Known as VoiceMate, LG's voice recognition technology has only recently entered the international stage,” says Mr Kim.


LG has been quick to incorporate voice commands, commanding a leadership role in this emerging space. However competition in voice command technology is fierce worldwide, especially in mobile phones with other alternative voice activated personal assistant field brands well-ingrained in the public's awareness.

The basis of LG's voice recognition software is intended to work in tandem with Google's own Android OS language-based systems, the latter being embedded within LG's own proprietary "Werniche" engine.

The technology works across two strands: Natural Language Understanding, which allows for intelligible processing of sentences, and Dialogue Management, which uses a vast database of available information to extract meaning. The project has developed as technology has evolved to enable a greater ability to grasp the complexity of human language, with notable LG products providing milestones leading up to the advanced voice command products available today.

VoiceMate represents LG's primary voice command platform and rivals other competitive voice recognition platforms in both function and in technological prowess also incorporating latest features like opening apps via command. Other functions include the ability to have texts sent, calls made, alarms set and web searches performed all by having a natural conversation with VoiceMate.

Functionally, VoiceMate uses "reasoning with a probabilistic model to find the best answer". This means that the context of the question is taken into consideration instead of just using a database to relay answers.

Progress has come about, thanks in part to steady progress in the technologies needed to help machines understand human speech, including machine learning and statistical data-mining techniques.

Sophisticated voice technology is already commonplace in call centers, where it lets users navigate through menus and helps identify irate customers who should be handed off to a real customer service representative.