Guide to Call-Automation


Tuesday, November 02, 2010 by Nuance Communications UK

In a period where excellent customer service is the key to unlocking business growth and prosperity, companies need to invest in their call centres and ensure a high rate of responsiveness at all times, even more so in the digital age. With the phone channel remaining the most popular route for customer service call, centre automation can offer a solution to many of these challenges by allowing customers to self-serve.

When to automate: It is important to understand where self-service can be used effectively in a customer care environment – and where it can't. The conundrum for many is how to provide superior levels of telephone customer service whilst reducing costs. Individuals are task oriented; they just want to get a job done quickly and with minimal fuss. So, being stuck in a queue waiting to speak to an agent, or being misrouted to the wrong department, is a recipe for poor customer service. Those companies that give their customers the tools and flexibility to complete tasks themselves, when and how they want, will be on the road to providing a superior level of service.

Solutions such as voice guided call steering allow customers to say what they want in their own words so they can be directed to the correct customer agent or automated service without having to go through a myriad of confusing touch-tone options. It reduces the time to route calls by as much as 50% and cuts misroutes by an average of 60%.

Testing, testing 1, 2, 3: Setting-up call automation using speech recognition involves the collection of more than 30,000 caller utterances that represent seasonal and monthly trends in call patterns, and using these to build a model of how people talk.

The speech application should be made available as a pilot to a limited audience of users. A good pilot is an iterative process. That means running the system, checking the data, and then tuning the system to ensure it fills the business needs before and after deployment.

Once a speech system is live, it is the business' responsibility to work in tandem with the vendor to continue to monitor the system's performance through ongoing data collection to tune the recognition parameters to improve performance. This also identifies additional optimisations based on data collected from the full caller population. This data can also serve to track changes in usage due to increased caller familiarity or changes in the caller population.

A phased launch: Speech automation return on investment is closely linked to user adoption. Because speech automation is interactive and customer-facing you can't simply throw the switch and walk away. The launch planning and production process typically takes two to three months and it is crucial that this is a holistic approach, encompassing the customer service and marketing teams, as well as the board. Through working with the marketing team to build consumers’ awareness of the system, properly set expectations, and promote usage, you can bring customers along for the journey. The effort and cost to educate customers will be paid back many times over the life of an application.

The long game: Once a speech system is in use, it will need to continue to be monitored through ongoing data collection and tuning the recognition parameters to optimise its performance.

Inevitably, businesses and their call automation systems will need to evolve to changing requirements to take into consideration changing consumer attitudes or new product offerings. As customers continue to demand around the clock availability, better response times, and greater consistency, call centres must be equipped to keep up.