What do customers say is one of the worst things about using an IVR (Interactive Voice Response) system when trying to reach a company? It’s the feeling that their time is not being valued and they’re being given ‘the runaround’ by a company that has implemented IVR solely to benefit themselves, rather than help customers. The endless wait to get through to customer support can try even the most patient of people.
IVR which allows customers to interact with a company’s host system via a telephone keypad or by speech recognition, can be a great way of helping customers resolve their queries without waiting for a human being; but speech recognition technology itself can sometimes be a let down.
Many companies have moved beyond asking you to ‘press 1’ for this or ‘press 2’ for that and now ask for more detailed information about yourself or your problem, sometimes in whole sentences. Often you need to give unique information, as instructed by a recording, to get further along the process chain.
Background noises such as traffic or other people’s chatter, plus a poor telephone line or non-native accents or dialects can cause havoc when trying to get your details across and add to the frustration of having to keep repeating yourself.
Many studies have shown that customers actually prefer self-service to waiting endlessly on the line for a live agent, but only so long as that self-service works efficiently. And that’s where speech technology can sometimes be the weakest link.
A major step forward has been the integration of Microsoft’s deep neural networks (DNN) technology and 7’s customer engagement platform, which gives customers a 25 percent better chance of being heard accurately – so raising the expected accuracy rate to 95 percent.
DNN is a form of Deep Learning architecture which can model complex non-linear relationships in language and so iron out any ambiguities by distinguishing between words and phrases that sound similar. For example, the words “recognise speech” and “wreck a nice beach” could sound almost the same over a phone line, but of course mean completely different things.
Microsoft’s DNN technology draws on the most advanced Microsoft speech recognition technology which uses over 10 billion vocal sounds from products and services such as Cortana (the intelligent personal assistant available on some iPhones), Xbox and Bing Search. All DNN technology seeks to emulate the human brain when it comes to understanding the spoken word and by learning from such a huge selection of actual human voices with a variety of accents, syntax and cadences, Microsoft’s DNN technology is extremely advanced. And it’s not just English, many other languages are available as well.
7 is the first company to integrate DNN Deep technology into enterprise IVR using Microsoft’s DNN technology.
The main benefit of this improved speech technology is that CSRs will be freed up from answering the same routine enquiries over and over again, and instead will be able to devote more time to dealing with more complex or unique queries. Customers will get answers to their questions more quickly one way or another – either through self service IVR or, if necessary, from a CSR.
According to a March 2015 Gartner report, “Why You Need to Rethink Your Customer Self-Service Strategy,” “by 2017, two-thirds of all customer service interactions will no longer require the support of a human intermediary.”
The last major step forward in speech recognition was over a decade ago when systems learnt to distinguish between discrete and continuous speech – that is, words spoken slowly with pauses in between them and words run together as they usually are in everyday conversation. Almost all modern systems are now capable of understanding continuous speech in the way it is normally spoken but the next step forward has been a while coming.
A poor IVR experience can easily spill over into a negative view of the company and the resulting loss of revenue for the company could have far reaching repercussions, so anything that improves the IVR customer experience is well worth having.