Could this be the end of road rage as we know it?
Ford might just have a solution in the works as it expects the cars of tomorrow to be able to pick up on minute changes in our facial expression and inflections in our speaking voice.
So advanced systems, equipped with microphones and in-car cameras, could learn which songs we like to hear when we're stressed and those times we'd just prefer silence. We may soon even have mood lighting in the car that can adjust depending on how chirpy – or perhaps filled with road rage – we are.
The American car firm is running a research project with RWTH Aachen University involving using multiple microphones to improve speech processing. With nearly 90 per cent of all new cars expected to offer voice recognition capability by 2022 according to IHS Markit, next on the agenda will be even more nuanced recognition.
Fatima Vital, senior director, marketing automotive, nuance communications, which helped Ford develop voice recognition in its in-car connectivity system, said:
We’re well on the road to developing the empathetic car which might tell you a joke to cheer you up, offer advice when you need it, remind you of birthdays and keep you alert on a long drive.
And Ford also has its sights set on turning cars into personal assistants that can switch appointments for you and order takeaways when drivers are held up in traffic jams. Cloud-based voice control is expected to be available on 75 per cent of new cars by 2022.
It has already teamed with Amazon's virtual assistant Alexa – this summer its in-car connectivity system, Sync 3, will enable drivers to connect to Alexa, offering 23 different languages and a range of local accents.
“Voice commands like ‘I’m hungry’ to find a restaurant and ‘I need coffee’ have already brought Sync 3 into personal assistant territory,” said Mareike Sauer, voice control engineer, connectivity application team, Ford of Europe.
“For the next step, drivers will not only be able to use their native tongue, spoken in their own accent, but also use their own wording, for more natural speech.”