Tag: warehouse voice
This column was originally posted in March 2015 and has been updated.
We talk about voice enablement with enterprises throughout the supply chain a lot, and here a lot of stories about their prior experiences with traditional voice applications. Their stories are maddening. Their stories are horrifying. Their stories are the kind that make anyone with P&L responsibility want to scream. Too often, these recounted experiences are stories of large up-front investments and then a bunch of unforeseen expenses post-deployment. The problem is the traditional voice application model, which adds costs in these four common areas:
Voice-dedicated hardware: Traditional voice apps require a separate, proprietary computer (typically worn on the belt or shoulder of the worker), that houses the speech-to-text and text-to-speech processing. However, if the barcode scanning mobile computers you’re deploying are fairly current (introduced to market in 2008 or later)), they already have the audio capabilities and computing horsepower to handle the voice processing, so you don’t need to buy proprietary voice hardware.
Middleware or “System Interfaces”: In most warehouse applications, you’re workers are already interfacing to a host system – your WMS, ERP or other supply chain management system. And, in most of these cases, your workers are using Terminal Emulation on their mobile computers to interact with this host system. There is no need to wedge additional middleware in between your host system and mobile device client in order to enable voice. You’re interest is to recognize productivity gains by adding voice to your existing mobile application, so there is no need to buy middleware to enable voice.
Host System Modifications: Recently, I wrote about the problems that can arise when your voice vendor wants to make changes to your host system. You’ve invested a significant amount of money in your host system, and you don’t need another vendor putting their hands in there (and changing you consulting services fees to do it). Adding voice to the mobile application should simply pass data back to the host system in the same way that barcode scanned or key-entered data is communicated. Your host system shouldn’t even need to know which method of data capture was used for a given data field, so adding voice shouldn’t require changes to your host systems.
Post-Deployment Host Modifications: Once your workers are voice-enabled and you’re realizing the productivity gains of voice-enablement, should you discover a process change that will further optimize your workflow, many traditional voice vendors will require that you contract them to contribute to the changes you want to make to your host system. They want to be included because they’ve already made changes to your host system to make their voice application work, so if you want to make any changes, they’ll need to ensure their application isn’t adversely affected. Deploying voice-enablement shouldn’t require host system modifications, so you shouldn’t have to pay professional services fees to your voice vendor every time you want to make a change to your host system.
If you’ve encountered any of these issues when considering adding voice to your picking or other warehouse workflows, it’s time to look at Speakeasy. It’s 100% mobile device driven (no proprietary voice hardware or middleware required), and does not require any modifications to your host system (which also eliminates the associated post-deployment costs). You get the productivity benefits of full-featured voice-enablement, but without all these additional costs that often make traditional voice applications cost prohibitive. Plus, you can deploy in as little as 30 days, so the productivity gains and cost savings can start adding up quickly.
Here at Wavelink, we’ve always had a special place in our hearts for speech recognition. It’s hardly surprising. We know first-hand the many benefits of voice recognition in the warehouse – improved productivity, efficiency and warehouse safety. Since the introduction of Speakeasy six years ago, we’ve watched the rise of applications like Siri and Google Voice, which bring voice recognition to the masses. We thought it would be interesting to take a look back in time at some of the history of voice recognition and how it’s evolved over time.
Before Siri, there was Audrey. Audrey was a speech recognition system developed by Bell Laboratories in the early 1950s. It was a pretty basic system and could only recognize the numbers one through nine. It also forced the speaker to pause between words, making it a bit cumbersome to actually use.
In the early 1960s, IBM made some improvements with their “Shoebox” device, which could understand 16 entire words: 10 digits and 6 arithmetical commands. Both Audrey and Shoebox, needless to say, were not very portable, making them highly impractical by today’s standards. Considering the low levels of computing power at the time, these were pretty significant gains. (more…)