|INFORMATION: More information is available from BCP on voice technology. Click here to request a copy|
Voice Technology for the warehouse is now mature and proven, but its only within the last couple of years that it has really started to take off in the UK. The technology has become more accessible and businesses have begun to understand better this technology and quantify the benefits it offers.
This Primer from BCP answers a host of questions for those considering the technology. If you decide that Voice Directed Picking is for you, then BCP will be happy to answer your further questions, and contact details are provided at the end of the paper.
What is Voice Technology?
Voice technology in the warehouse involves the use of a wearable computer with a headset and microphone so that warehouse operatives receive voice instructions and confirm their actions back to the system verbally. The wearable computer communicates with the Warehouse Management System (WMS) using a radio frequency (RF) local area network (LAN).
What can I use it for?
The most common application is Order Picking where improvements in accuracy and productivity offer a speedy payback, but you can also use it for Stock Checking, Goods Received, Pallet Put-away and Letdown.
What equipment do I need?
You will need voice terminals such as Vocollects Talkman T2, a voice-directed, wireless, belt-worn computer, utilizing advanced speech recognition and speech synthesis technologies. The voice terminal provides users with real-time radio communication to the Warehouse Management system. You will need a radio frequency (RF) network and a PC on the network to act as a communications server.
Can I use my existing RF network?
If you have a modern radio frequency network, it is likely you can use the existing network. It will be necessary to conduct an RF survey to check RF coverage because the radio reception of a belt worn unit can differ from that of hand held or truck mounted terminals.
What software do I need?
You will need Warehouse Management Software capable of interfacing with the voice terminals. Existing Warehouse Management software can often be retained by using a middleware software solution to interface to the voice terminals, but greater benefits can be obtained from Warehouse Management software with fully integrated Voice capabilities, such as Accord from BCP.
What are accuracy improvements can I expect?
Dramatic improvements in order picking accuracy can be made, and accuracy of 99.9% (one error per thousand picks), or even better, is usually achieved. The improvements that you obtain will depend on the type of goods being picked and your current method of order picking, but if you are moving from a paper-based system to voice directed picking, picking errors are usually reduced by between 80% and 90%.
What productivity gains can I expect?
Order picking productivity often improves by 10% to 20% because the hands free and eyes free operation of the terminal speeds up picking, and trips back to the assignment desk are eliminated. Administrative productivity is also improved by eliminating the work of printing and distributing picking documents, as well as the task of keying in picking amendments, picking confirmations and catchweights.
What other benefits will I get?
If you are eliminating paper picking labels, this brings a significant saving in the cost of the labels alone.
The real time radio communication enables real time stock updating. This in turn allows just in time triggering of letdowns to replenish picking faces, optimising the use of fork lift trucks and preventing waiting time or re-picks due to empty picking faces. Cycle counting can be built in to the replenishment (letdown) task, improving the efficiency of the stock checking process or the frequency of stock checks. The improved accuracy of stock recording can lead to improved service levels and less time spent investigating stock discrepancies. These additional benefits are of course dependent on the functionality available in the WMS.
Safety can improve as the hands free and eyes free operation leads to fewer accidents. Eliminating paper also means less waste paper or label backing sheets, providing a cleaner, tidier and safer warehouse.
Training for new pickers is speeded up by the use of voice, as a voice directed task is easier to learn than interpreting a paper task. Training time can often be reduced by as much as half.
What is the payback?
The biggest payback invariably comes from the accuracy improvements rather than increased efficiency. If you operate more than one picking shift then the costs are shared across picking shifts and payback can be achieved in as little as 6 months. If you operate a single picking shift, then a payback of one year to eighteen months is more realistic.
Can I use it in the freezer?
Yes, voice technology is ideal for use in the freezer, and the hands free operation of the terminal offers even greater productivity improvements as gloves hamper the use of paper or radio data terminals. The Talkman T2 terminal, for example, operates in temperatures down to minus 29C
Does it work in a noisy environment?
Yes, the Talkman terminal, for example, uses a speech recognizer which was specifically designed for noisy warehouse and industrial environments, filtering out and rejecting intermittent and background noise. Speaker dependent voice recognition and the limited vocabulary used enable the high degree of accuracy that is needed for efficient use.
Whats the difference between speaker dependent and speaker independent voice recognition?
Speaker-dependent systems require each user to train the system for his or her individual speech pattern. Voice training typically takes ten to fifteen minutes per user. Training allows the system to be much more accurate and robust in an industrial environment where there can be a wide range of accents, dialects, and languages, and much extraneous noise.
Speaker independent technology is designed to match the speaker's voice to previously created, generic voice patterns, and is less suitable for the warehouse environment.
Does each user just have to do the voice training once?
It is often sufficient for a user to perform the voice training just once, and it takes only ten to fifteen minutes. However, during voice training users do not always speak as they normally would when working in the warehouse and systems such as Talkman allow retraining on the fly. If the terminal consistently fails to recognise a particular word, the user can retrain their voice in the middle of a task just by pressing a button on the unit and speaking that word once more.
Can it handle different dialects and accents?
Yes, each user trains the system for his or her own voice, which allows the speech recognition technology to accurately recognize any users speech regardless of accent or dialect. If desired, a user can even train the system to recognise responses in a different language.
Does each worker need his own unit?
You need enough units for the number of workers on the largest shift, plus a small percentage of spares. However, users usually have their own individual belts and headsets.
How often do the batteries need charging?
The time that units can operate on a single battery charge depends on a number of factors. The power consumed by the radio card varies significantly between different radio cards, the low temperatures in a freezer reduce battery life, and the amount of radio communication needed by the application also affect power consumption. Typically, times are between 4 and 8 hours. In ambient temperatures, a battery charge may last a whole shift, depending on the other factors, whereas operation with a faster RF network in a freezer would almost certainly require a battery change. Standard and heavy duty batteries are available.
Are the units robust?
Yes, specialist terminals such as the Talkman are designed to be rugged and have been drop tested with multiple drops of 5 feet onto concrete. Non-rugged hand-helds devices with speech capabilities are less suitable for warehouse use.
How much does the unit weigh?
The Talkman, for example, weighs less than a pound, including a standard battery.
How easy is it for workers to get used to it?
Workers are usually enthusiastic and get used to it very quickly. Most new order pickers can be trained quicker in voice directed picking than in paper-based picking.
Can I use it if I have a cold?
The speech recognition is not usually affected by a cold, but laryngitis or hoarseness may affect operation. It is advantageous to use terminals which allow voice training to be done on the fly if you experience problems.
Can hearing impaired people use it?
If the users are not 100% hearing impaired, they can often use the system.
What happens if a user is out of range of an RF access point?
This will depend both on the capabilities of the terminal, and on the design of the application software being used. The Talkman terminal has onboard intelligence and can continue to operate out of RF coverage, but the functions available will depend on the application software. During order picking the entire order is typically downloaded into the terminal so that a picker would not normally notice a break in RF coverage. However, in some exceptional circumstances the Talkman will need to communicate with the server, and the application waits until the unit is within RF range again.
How does a picker confirm what he has picked?
The picker normally reads back the last 2 or 3 digits of the barcode so that the system can check the correct item has been picked. The picker does not have to read back the entire barcode.
Is the voice transmitted over the RF network?
No, with most systems available today, speech synthesis and speech recognition is carried out on the voice terminal, and data only is transmitted over the RF network. If voice were transmitted over the network, the bandwidth would restrict the number of users and high performance voice servers would be required.
How many terminals can I add to the system?
There is no practical system limit to the number of terminals that can simultaneously use the system, provided voice is not transmitted over the network. Obviously, the main server must be capable of processing the transactions in real time.
How long does it take to download the users voice profile to the terminal?
Typically the users voice template is downloaded to the terminal over the RF network at the start of a shift, and takes only a few seconds.
Shouldnt I wait for RFID instead?
No! In a case picking environment, then once all manufacturers are tagging cases at source, RFID will be an excellent technology for confirming the item picked. However, the picker still needs to be told what item to be picked and to be directed to the correct location. Voice will remain the best technology for that. Ultimately the best solution will be a combination of Voice directed picking with RFID confirmation of items picked. Where split cases or singles are being picked, this will require RFID tagging of individual items. Until then, Voice Directed Picking is the best available option for most picking environments and offers a rapid return on investment.
Related Voice in the Warehouse Videos
This video from Vocollect compaires voice in the warehouese to traditional scanning technologies.
Watch how the US company Pep Boys implements voice directed warehousing.
Microlise voice picking gains Signet Group more than double the productivity with same accuracy in high value jewellery warehouse
See how Voice-Directed Distribution opens a two-way dialogue between your DC team and your warehouse management, ERP, or inventory management system.
Each day, over 100,000 workers in hundreds of companies on six continents use Vocollects voice-directed work solutions to increase fulfillment accuracy, boost productivity and improve customer satisfaction this is an example, Easydis/Casino Video Case Study.
The introduction of voice picking technology from microlkise helped Dixons to price goods ready for store delivery without increasing picking times in their warehouse