Speech Recognition: The Answer to Customer Service?
What they gain in convenience, they lose with modern-day annoyances that come with the new technology. You can check your savings account balance at any time of night, but not until coping with five rounds of touch-tone multiple-choice questions. You can order clothing online, but if there are delivery problems, e-mailing customer service can be frustrating, especially if you have to wait hours or days for a response.
Speech recognition technology for years was viewed with a more critical eye. Not only was the technology seen as clumsy, with people having to overly enunciate and practically shout into the phone to be heard, but many times the technology simply did not work properly.
The concept of talking to a computer or telephone and having it accurately respond to your commands was seen as science fiction.
Passed up as unreliable a decade ago, speech recognition today receives high marks for its high completion rate, accuracy and large vocabulary.
Retailers are so confident of speech recognition's power that the technology now manages customer service. This is no small task in a culture where consumers expect next-day delivery and the ability to do business at any time of the day or night.
According to GartnerGroup, Stamford, CT, "Speech recognition technology finally works. [It is] an emerging 'self-serve' technology that will enhance customer service while reducing personnel costs."
While customer service today is dominated by Dual Tone Multi Frequency systems that require the sometimes-tedious use of touch-tone phone keypads, tomorrow belongs to the ease, efficiency and cost savings of speech recognition. While convenient, DTMF systems are notorious for their tedious routing. Sometimes, tasks that would take less than a minute with a live person can be frustrating and time-consuming as customers are subjected to several multiple-choice options.
Companies prefer speech recognition software and hardware for the same reasons they appreciate DTMF. It is cost-effective, it allows their customers to use it at any time, and it delivers a consistent message.
A speech recognition program can cost far less than a customer service representative. Combining salary, recruitment and management costs, as well as the expenses of facilities and benefits, a CSR costs an estimated $34,800 each year. With a speech port, the installation, maintenance and overhead costs total $3,333 a year. Broken down by call, customer service costs $1.47 per call through a CSR and 9 cents for a speech recognition port - about 1/16 the cost.
Speech recognition should not be used for every DTMF application.
Applications with a very short start-up time or a very short life are not a good fit for speech recognition.
But when the elements are right, companies can come to view speech technology as the answer to their customer service needs.
Previously viewed as unreliable, speech technology is now affordable, reliable, proven and in demand. For companies willing to take the gamble, speech technology promises to be a rare breed: technology that enhances customer service with virtually none of the trade-offs that have made DTMF technology an annoyance.
Speech recognition is so advanced that customers only have to "register" once using their voice, and their voice patterns are secured on a small file for future transactions. When the customer calls the system again, he needs only to say a few key words (usually a natural element of the call) and has full access to the account.
Each voice pattern is unique and cannot be duplicated or changed. Even if the user has a sore throat, the customer will still be recognized.
Speech recognition eliminates the need for tedious extra steps in the identification process that are unreliable to begin with.
Speech recognition systems can be used as a two-tiered security system, prompting users to speak their account or name and simultaneously checking the validity of both the information and the voice. If there are discrepancies, the caller is routed to a live representative.
Today, Fortune 1000 companies such as Sears, Hewlett-Packard and Federal Express use the technology to offer customers technical assistance with computer problems as well as stock quotes and to provide 401(k) account information. For Federal Express, the technology has been so useful in helping customers track packages that it is now used for scheduling pickups and ordering supplies.
Another case where speech recognition has left its mark is with United Airlines. It was a huge test for the technology since the airline handles an estimated 1.5 million calls each year to inquire about United's 2,300 daily flights to 130 destinations. After a four-month development period, a speech recognition program was launched at the end of 1997. The system provided immediate service, 24 hours a day, seven days a week, and it answered queries with direct dialogue and natural language.
Before the airline implemented the speech technology, customers checking on the status of an airline flight were asked to press 1 for flight information and then were required to choose between pressing 1 for arrivals or 2 for departures. After that, they were asked to type in the day of the flight. Then, the customer had to punch in the flight number. If they did not know the flight number, they had to press a different key, and so on.
Customers using the speech recognition system had a far easier time. They only had to say, "I want to check an arrival flight for today. I don't have the flight number."
Already, four rounds of questions and answers were eliminated.
The system had a completion rate of 97 percent. It has been so efficient that more than 70 percent of customers voluntarily choose to deal with the speech recognition system when prompted.