Showcase – Voicebot

Applying speech recognition and bot technology for automated answering of requests results in an impressive increase of customer satisfaction.

Interaction with customers is key for the success of a company. But what do you do when customers mainly want to contact you by phone and your back-office resources are scarce? Is it possible to reduce the load on the call center by introducing a voicebot without straining the customer relationship? Can a voicebot even be built in Swiss German with reasonable effort? In order to answer these questions, we carried out a proof of concept with the Road Traffic Office of the Canton of Aargau.


Observe – Magic Match

Challenge: The Road Traffic Office of the Canton of Aargau receives over 330,000 telephone enquiries per year, which it is unable to handle satisfactorily for capacity reasons. At peak times, less than 50% of the requests can be treated in a timely fashion. Outside office hours, an answer machine provides limited information. Because of the poor accessibility, customer satisfaction is low, which results in pressure on office staff.


Solution: Combine speech recognition and bot technology to implement a voicebot that enables automated answering of simple requests.


Incubate – Proof of Concept

Hypothesis: We believe that it is possible to build – with relatively little effort ­– a voicebot that can answer the most frequent questions independently. We also believe that this will increase customer satisfaction and relieve employees so that they can perform their actual work more effectively.


Approach: To find out whether our hypothesis is correct, we ran a proof of concept (PoC) based on a cloud-based voicebot infrastructure put together from different commercial and open-source products. We selected five frequently asked questions and built language samples in Swiss-German to train a natural language understanding model (NLU). In iterative tests with employees and customers, we continuously optimized the solution to improve both understanding of questions and customer experience along the call flow. Finally, we switched on the solution selectively outside of office hours.


Result: Our PoC solution successfully handled simple customer requests - from welcoming customers to answering their questions. Despite the small amount of data and the short training time, the recognition rate was surprisingly high (over 70%). Contrary to our expectations, acceptance of the solution was also high: the majority of users were open to and even enthusiastic about using this new possibility to get information.


Convert – Value for Customers

Voicebots offer a natural and very effective way to reduce load on call centers. They sort calls and answer simple questions or transfer calls to the right call agent. This brings value to both clients and their customers:

  • Customers benefit from getting answers without waiting times, even outside business hours. Also, they like the intuitive interaction with the Voicebot. They no longer have to struggle with menu structures, decision trees and phone keypads ("for German press 1").
  • Call center agents benefit from having less pressure in their daily work. They have to invest less time in answering repetitive questions and appeasing frustrated customers and have more time for more satisfactory tasks. This increases employee satisfaction and results in higher motivation.

Our PoC showed that customer satisfaction increases significantly due the higher availabilty (7/24) and faster response times. The relavtively low investment combined with an impressive result suggest a quick ROI for a productive installation.


Taking it to the Next Level

Voicebots can do even more than triage and answering questions. They can handle complete end-to-end processes including integration of backend systems. They can also help companies fullfill security and compliance tasks such as user authentication or protocolling of customer conversations.


Based on the experience during the proof of concept, we have implemented a similar solution for the Road Traffic Office of the Canton of Zurich. Find more information about this in the recently published NZZ article.


Spitch AG

We use products from our Zurich partner, Spitch AG, as the basis for the voicebot. For Adnovum, it was crucial that the voicebot conversations be as natural as possible, i.e. for Switzerland also in Swiss German.

‹‹Through the automatic processing of customer inquiries, the voice bot considerably relieves the employees who can concentrate on more complex customer concerns.››
Dr. Martin Sprenger, Head of Departmental Services and Personnel, Aargau Road Traffic Authority

Contact us – we are pleased to help!

Should you have questions or wish to talk to an experienced advisor, contact us – we will be pleased to help.

Stéphane Mingot Head of Adnovum Incubator

Mark Bosshard Head of Conversational AI