Adding a Voice to Bluetooth

Sensory, which manufactures embedded speech technologies in consumer products, and Foxlink Group, a developer and manufacturer of consumer electronics, announced today a strategic partnership to create Bluetooth products controlled by a Voice User Interface (VUI). The initial focus will be on the headset market and on hands-free car kit products. This announcement comes more than a month after Sensory announced its partnership with CSR to create speech-powered Bluetooth chips.  

Given the size of a Bluetooth headset, VUI is the most efficient control. Buttons are unwieldy and often difficult to use given most headset designs. Additionally, users have to be trained on which combination of buttons to push to operate a certain feature. By contrast, voice controls are more intuitive. Additionally, voice controls allow for safe operation of the device during an eyes-busy, hands-busy activity like driving or street fighting.  

The partnership between Foxlink and Sensory should expedite the time to market for Bluetooth headset companies wanting to integrate VUI. "Our customers want improved user experiences for their headset products," said James Lee, Foxlink’s operation president. "With Sensory’s voice recognition and speech output technologies, we can add more features while making the products easier to use.  This is needed for continued market growth."

According to some analysts, however, the incorporation of VUI in Bluetooth is only a small demonstration of speech interface capabilities.  

"I think this is an intermediary step for what’s going to come," says Datamonitor analyst Daniel Hong. "Finding the optimal blend of speech recognition processing is needed to increase accuracy, which in turn improves user interface."  

While the market for voice-powered Bluetooth headsets might seem tailored to drivers, the advent of telematics, wherein a driver’s cell phone pipes through the car radio, holds more promise for analysts.
 
"(Bluetooth headsets are) an example of a very simple command and control operation," Hong says. "Sure, there are a lot of advantages, however the bigger picture is using speech as an interface in pervasive computing."