Tag: voice-enabled wireless applications
The Cofares Group supply products ranging from medicine to health and beauty products to 13,000 pharmacies in Spain from nearly 30 distribution centers. Often they deliver orders that range from one to 20 items to each pharmacy three or four times a day. They need to be able to make these deliveries quickly and accurately.
“Our customers evaluate us based on our ability to deliver complete and accurate orders,” said Abelardo Vaquerizo, duty manager of Cofares Group. “It is a hectic environment where we need to fill orders quickly, but it doesn’t matter how fast we are if we get an order wrong.”
Distribution centers process a large number of orders on a daily basis and Cofares is no different. Most of the medicines are filled by automated machines, but health and beauty items are picked by hand from the warehouse and loaded into delivery trucks. It is a logistical challenge to ensure that the right items get in the right order on the right trucks every time in the most accurate and efficient way possible.
With the number of orders being processed every day, it is a logistical challenge to ensure the right items get in the right order on the right trucks every time. Cofares, through its technology partner, Felguera TI, an affiliate company of Duro Felguera, selected the Speakeasy voice solution from Wavelink to add text-to-speech and speech-to-text functionality to their warehouse applications. The ability for Speakeasy to combine voice with other types of data entry, such as bar code scanning, provides a further crosscheck to ensure that tasks are accurately completed.
“We have initially implemented Speakeasy in two of our larger distribution centers in Madrid,” says Vaquerizo. “Workers are able to speak into their device the item they need to pick and have it speak back to them with a bin location. Once there, they can scan the barcode on the bin, select the items and verbally confirm the item and quantity. This gives us even greater accuracy while also helping them complete the task faster.”
In locations where Speakeasy is being used, Cofares handles approximately 1,200 orders per day. Prior to Speakeasy, there was an average of 20 to 30 errors in those orders, which was still a 97.5 percent accuracy rate. However, with each incorrect order, there was the cost of returning the product and a loss of the sale as well as the negative impression it left with the customer. With Speakeasy, Cofares has virtually eliminated errors with an average of zero to two errors per 1,200 orders.
Cofares were also able to benefit from an intuitive user interface, which allows any employee to pick up a device and use it immediately without needing to create a voice profile. Vaquerizo adds, “Our employees have been very happy with the ease with which they can use Speakeasy. We have experienced very short training times, where we have been able to quickly get a new worker using the system. This was a big cost benefit in terms of our ability to be immediately productive.”
Since Speakeasy is a client-side solution that does not require the addition of voice servers or modification to the host applications, the implementation of the voice solution went smoothly and was completed in just a matter of days. Adding voice to streamline your operations should be simple, straightforward and effective, in today’s non-stop supply chain environment it just has to be.
With the rise of speech recognition technology such as Siri for the iPhone, Dragon for PCs and OnStar in vehicles, it seems voice-enabled technology is becoming ever more prevalent for consumers. In fact, Melanie Pinola of PCWorld states “It isn’t hard to imagine a near future when we’ll be commanding our coffee makers, talking to our printers, and telling the lights to turn themselves off.”
As with the BYOD trend, once consumers become accustomed to using specific technology in their personal lives – they expect the same functionality in the workplace. We see this as many bring smartphones and tablets into the corporate space and we can expect that voice functionality will follow the same path.
But does voice technology even make sense for businesses? Absolutely. This is especially true in a back-office environment, such as a warehouse. Adding voice capabilities has been proven to deliver 99 percent accuracy, as well as a 10 percent improvement in productivity to warehouse applications such as data-entry, picking and processing. Voice also dramatically improves safety by allowing workers to work in a hands and eyes-free environment.
While the benefits for voice-enabled technology are many, both consumers and corporations alike are sometimes fearful that there may be negative implications as well. Slate Magazine recently reported that the country of Ecuador has successfully completed installation of “the world’s first biometric identification platform, at a nation-wide level, that combines voice and face identification capabilities.” While the technology behind such a massive project is impressive, many are worried about the issue of privacy for Ecuadorian citizens. In addition, Sherry Tufts, a professor at MIT, recently told the New York Times “I’m not saying voice recognition is bad. I’m saying it’s part of a package of attachments to objects where we should tread carefully because we are pushing a lot of Darwinian buttons in our psychology.” Tufts believes that by speaking with inanimate objects, humans behave differently than they would if they were simple typing or clicking a mouse. “Humans are wired for speech and tend to respond to talking devices as if they were kindred spirits,” she told the Times.
But don’t the positive outcomes outweigh any potential negatives? In my opinion they do, especially when it comes to applications where typing or manually inputting data into a machine can be detrimental or even hazardous. This applies to a number of types of jobs – from a warehouse worker taking inventory from a tall ladder to a doctor recording patient vital signs.
I believe that the applications for voice-enabled technology are limitless and will skyrocket in the coming years. As consumers interact with this technology more and more in their personal lives, they will expect it in the workplace too. I think we’ll see speech recognition move beyond the few business applications where it currently resides, such as supply chain, healthcare and field services, to the desk of nearly every end-user in the corporate enterprise. They’ll be commanding their computers, phones and other objects with their voices and fingertips. And the keyboard may just become obsolete. So, tell me, do you think voice-recognition technology makes sense for your business? Leave a comment below and explain why or why not.
I was just re-reading Maida Napolitano’s article on Voice Picking from Logistics Management magazine mid-2010 (“Three Voices, Three Solutions”, Maida Napolitano, Logistics Management, July 2010). In it, Ms. Napolitano highlights three different voice picking solutions, from three different providers. All three solutions have different architectures. This provides the foundation for the segmentation of the voice solutions in the article.
Although the article is an excellent overview of three of the possible architectures for voice solutions, there is one small problem. There are actually FOUR different architectures available today, providing (at least), four different voice platforms.
Napolitano’s article covers the following designs:
- Proprietary Solutions – These are speaker-dependent solutions requiring custom voice hardware, and are the oldest voice solutions on the market.
- Open Hardware – These can be speaker-dependent, or -independent, and utilize off-the-shelf mobile device hardware with thick-client applications provided by the voice solution provider.
- Intelligent Networks – These are speaker-dependent, or -independent, and utilize a thin-client “approach”, with “more intelligence placed in the network” (Quotations mine).
Although this description gets very close to enumerating all the differences in voice architectures, it is missing one key design. Also, it tends to separate two solutions that share a fundamental design element, and lumps in the missing element as part of the last one.
Let me explain.
Posted by Jay Cichosz
Every now and then, we have the opportunity to tell new customers and/or Partners about what it means to provide solutions for the entire mobile ecosystem, and it struck me that it might make a great topic for a blog post.
When you look at our solutions, the best way to visualize the “how do they all work together?” question is to envision an enterprise within the four walls. Let’s say that the enterprise is divided into the following “sections”, all of which come with their own needs and requirements.
In every Warehouse, applications are being run for a variety of tasks. This is where we begin our circle of mobile ecosystem solutions, via Studio and TE which allow organizations to deliver the aforementioned applications to mobile assets, such as handheld computers. From there, it’s possible that some of those applications are web-based, and therefore require an Industrial Browser or Velocity to render and properly run them. For further productivity, many companies are now looking to voice-enable these very same applications, which as you’ve seen in our Goya Foods video, our Speakeasy product does quite well.
Let’s continue to our next “section”.
Last week, Multichannel Merchant had a great article that focused on how to improve warehouse productivity. He had nine tips for doing so ranging from creating a picking path to listening to employee feedback.
We’d like to add a tenth – using your voice.
Voice picking isn’t new to the warehouse. In fact, our voice picking product, Speakeasy, has been around for years, but just within the last couple of years companies have really started to implement it and see huge returns.
Take Goya Foods for example. They have been using Speakeasy in their Prince George facility. Within the first few months of using Speakeasy, they noticed improvement in three areas – accuracy, efficiency, and safety. Like Goya, most companies see the following:
Mispicks can lead to significant expenses, costing most companies anywhere from $5 – $50 per error. With that in mind, you can see how the savings quickly add up. (To see for yourself, contact us for a copy of our Speakeasy ROI Calculator)
On average, pick teams will complete their tasks much faster than before. With voice, pick teams move from sequence to sequence in rapid time.
With voice commands, pickers move from point to point more safely. This makes plant managers much more at ease.
Another thing to point out is that management costs of Speakeasy are minimal because the product is advanced enough that pickers don’t need to go through technical training to calibrate it for their own use.
Not to mention it is really easy to use, as our own Greg Berger demonstrates for Warehouse IQ at ProMat last year.
Our good friends at BCI, a Wavelink Platinum Partner, recently shared an article on the possibilities of voice applications not having much of an impact. When asked about our thoughts, we said, “well sure.” But there is a big “but” that followed our response and I wanted to point out some very critical points when discussing voice. The biggest issue is the issue of cost, which all companies are concerned with, and this is 100% true with traditional voice systems.
“[Bill Kuipers, president of operations consultancy Spaide, Kuipers & Co] thought he was in the minority about pick-to-voice technology. “I’m not surprised based on my own observations, but I thought I was in the minority. Lots of clients consider but ultimately reject it (usually due to the cost of hardware, and the required software integration). It tends to be more expensive than comparable RF Scanning devices.
‘Plus, you almost always have to buy some sort of intermediate software system, whereas most applications already support basic bar code reading – or can easily incorporate it.’”
This is the fundamental problem with yesterday’s voice technology. It requires you to buy new devices and servers, deal with lengthy implementation times, a replacement of existing business processes, and an overhaul in training. In that case, who would want to deal with it?
And that’s where the value of a voice application like Speakeasy comes in. It doesn’t require new hardware, can be implemented in as little as 30 days, works with your existing applications, and as such, is easy for workers to learn. If you’re curious about the differences, I highly suggest checking out the recent webinar we held entitled, “Say Goodbye to Legacy Voice.”
As some of you may have seen last week, Goya Foods was recognized with a Mobilizer Award for supply chain operations by Mobile Enterprise magazine and their use of Speakeasy. The award highlights trends that we’ve seen for a while now, in that more and more companies are trying to leverage their applications while maximizing as much productivity out of them as possible. An easy way to do this is by voice-enabling applications without having to redo the entire application. Goya tapped into this and the early results are telling.
Look for us to have more and more information on the Goya example in the coming weeks and months. Additionally, if you’re looking for more information on Speakeasy and voice products, we recently held a free webinar that you can view on-demand.