The future is voice control

“Mobility has changed from the Model T to the iPhone,” says Pim van der Jagt, managing director of the Aachen research centre. Solving the problem of how to integrate the mobile communications technology of today and tomorrow with transport technology is a key challenge for the big car makers.

Ford Sync uses Bluetooth to communicate with iPhones, Blackberries and Android smartphones, allowing for calls to be initiated by spoken command and text messages to be dictated.

Van der Jagt is frank about Ford’s recent woes, acknowledging that product quality was a key reason for its financial problems. With that in mind, focusing on improving the driving experience through the application of bleeding-edge technology is a cornerstone of its continued recovery, he says.

Of course, it’s not easy for a car maker to become a tech company, and the latest generation of Ford’s in-car communication and control system, featuring an 8in touchscreen, and dubbed MyFord Touch, has been beset by reliability and usability problems.

The difficulties with MyFord Touch illustrates the challenge faced by all companies as they face a software-dependent future. Still, Ford Sync has so far been deployed on four million vehicles in the US, and the company is aiming for 13 million Sync customers worldwide by 2015, including 3.5 million in Europe.

Ford is also pitching plenty of ideas about how imminent technology might radically improve the driving experience, only some of which rely on voice recognition.

According to van der Jagt, Ford and other car manufacturers are co-operating on a secure communication protocol between cars that will allow for real-time traffic and safety information to be transmitted between vehicles, potentially vastly improving road safety. (A vaguely similar technology featured in an aspirational, and overly optimistic, Ford promotional video all the way back in 1966.)

The realistic timeline for the implementation of those ambitious plans is many years in the future, but voice control is a more immediate addition to our driving environment – the problems posed by parsing human speech patterns, eliminating background noise and understanding various accents are hugely challenging, but the solutions have improved dramatically in recent years.

“Voice technology has matured beyond simply recognising what has been said, to now include natural language processing that understands what we mean, to access content and achieve specific outcomes,” says Stefan Ortmanns, a senior vice-president of mobile engineering at Nuance.

Ortmanns suggests that the technological limitations that for so long restricted voice recognition to rudimentary functions such as answer-machine services are being quickly overcome – the Siri effect calls is evidence enough of that.

Massachusetts-based Nuance has maintained a relatively low profile for a company that will help shape our technological future.