This is the fifth in a series of blogs discussing technologies and trends in voice picking and multi-modal warehousing solutions.
Voice-Plus multi-modal devices are helping warehouse professionals bring the productivity gains of voice recognition technology to a widening range of applications.
Over the last few years, it’s been my observation that picking productivity has been significantly improved by voice direction and recognition technology that enables workers to communicate interactively with the Warehouse Management System (WMS). Study after study confirms that voice technology has made a significant impact on warehouse productivity. This is especially true in hands-free, voice-driven piece-picking and replenishment processes. By and large, most voice recognition users are satisfied with the value voice picking technology has helped them unlock in their warehouse operations. According to a recent Aberdeen Group report, approximately 80 percent of voice users plan on continuing to use and/or enhancing their voice technologies.
The Benefits of Voice
In the beginning of the voice recognition era, voice-aided order picking was the hot button. With wearable voice technology, workers could be directed to exact locations, told exactly what items to pick, verbally verify their actions, and were then directed to the next location. Empowering workers with wearable mobile computers with optional voice direction capabilities helped drive an increase in productivity, accuracy and ultimately ROI.
But because they were focused primarily on purely voice-driven order picking, first generation voice technology devices were mostly computers dedicated to speech only. Typical devices had no screen, no scanner interface, and no keyboard. That meant there were some limitations into the range of workflows that could be supported by early voice directed solutions. Furthermore, speech recognition technology was most adopted by and suited specifically to piece-related processes, as opposed to carton- or pallet-related activities.
Despite these issues, warehousing professionals were understandably eager to add the productivity benefits of voice recognition hardware and software to other processes, especially those that required identification and data capture that could be transported directly to the WMS. A study by Voice Information Associates (VIA) projects an annual 30% increase in the use of voice for non-picking applications between 2010 and 2017, which significantly outpaces the growth projected for voice picking alone over the same period.
There was also another consideration driving new requirements for the next generation of voice solutions: the desire for shared devices. In a modern and uber-efficient warehouse, the same devices are often used for different functionalities from shift to shift. Rather than purchase devices dedicated to a single modality like speech recognition for picking and then a different set of devices for cycle counting and put-away, companies wanted singular multi-modal devices that could perform different tasks and run multiple software applications, depending on when and how they are being used.
The solution is today’s new class of versatile “voice-plus” multi-modal devices that are now available in many different form factors. Using these devices, workers can effortlessly move across a wide range of processes that include replenishment, receiving, put away, quality assurance, trailer loading and many more whether within a single shift (in the case of task interleaving) or across multiple shifts. Furthermore, the new multi-modal devices are designed not only for piece-level activities, but also enable the growing movement toward pallet-level activity, including significant time spent in forklift cages. Available in wearable, handheld and vehicle-mounted form factors, these devices combine the efficiency of voice-recognition hardware and software with the scanners, screens and keyboards needed for fast, flexible, accurate data capture and reporting.
Lower TCO, Higher ROI
The bottom line benefits to upgrading voice-only devices to voice-plus devices are substantial. The ability to use a single device for multiple uses beyond just voice picking alone can significantly lower total cost of ownership, which combines with the productivity gains of multi-modal technology to increase ROI. So when the question is: Should voice-recognition technology be left to its own devices in the warehouse? The answer is: Not anymore.
Mark Wheeler is the Director of Supply Chain Solutions - North America for Motorola Solutions
Read other blogs by supply chain expert Mark Wheeler.
Are you ready to pick a new direction now? Motorola Solutions is ready to help you improve your operation.