Turning speech data into great outcomes

Back to All Posts

Andrew Moorhouse 5th March 2019 3 minute read

Turning speech data into great outcomes

Our latest edition of Intelligence takes a look at ‘The Power of Data’ – exploring how organisations’ use of customer data will continue to evolve and shift in 2019. Here, Blue Sky’s Director of Insight Andrew Moorhouse explains how when used correctly, the data from computational speech analytics can vastly increase customer experience scores.

For any large customer service organisation, the appeal of computational speech analytics is obvious. A speech recognition system can analyse all points of a customer conversation with 70% accuracy, identifying any phrases that indicate the customer’s satisfaction levels. Contrasted with a traditional Quality Assurance team, who typically manage to listen to only 0.7% of customer conversations yet cost around £4million a year, it is no wonder that businesses are increasingly implementing speech analytics into their customer service.

However, getting speech analytics right isn’t as easy as many of these businesses think – it’s a complex process, and there are numerous pitfalls an organisation can run into. “It’s a long way from being an ‘out of the box’ solution,” explains Andrew Moorhouse, Director of Insight at Blue Sky (a subsidiary of Capita). “It takes a whole new set of skills to analyse the data in a manner that will actually drive up customer satisfaction levels. That means doing it without bias, and not in a way that encourages advisors to game the system.”

Andrew recalls working with an organisation that had removed their quality assurance team entirely and replaced them with a speech analytics system. Contrary to their expectations, customer satisfaction levels were decreasing while complaints levels remained the same. On looking closer at those customer conversations, Andrew found some fascinating examples of the organisation’s overly simplistic approach to speech analytics.

“The out-of-the-box speech analytics programme was linked to a dashboard system that would give the advisor a green tick if it heard an apology, because it was coded to think apologies were good,” he recalls. “Consequently advisors were apologising for everything! It was as if the opening words in every conversation were ‘I’m sorry for your loss’. And it was just making customers more and more dissatisfied.”

The organisation had failed to account for the fact that while apologies and politeness may have impressed customers 10 years older, modern customers now just consider this a hygiene factor. 4 years on the organisation has raised its CSAT levels again, but only after rehiring its quality assurance team and rethinking its approach to speech analytics.

“The combination of human and AI – that augmentation of human intelligence with artificial intelligence – can do more than AI can manage on its own” says Andrew. “I think there is huge potential in quality assurance teams taking that function on; retraining and reskilling to bring what they already know about excellent customer experience to the AIs that go looking for it.

“We’re breaking new ground in human augmented speech analytics, and I think it’s going to be a hugely important element of customer management in the coming years.”

To read the full interview with Andrew, and get more insight from our experts about the use of data in a post-GDPR world, check out our latest edition of Intelligence.

Why fixing a customer’s complaint really is the least you can do

by Tracey Roberts 26/07/2019

5 minute read

Read the article

Why being alert to emotional context can boost customer satisfaction and benefit the bottom line

by Kerry Edwards 25/07/2019

5 minute read

Read the article

Keeping your promises? Here’s what your customers think

by Jo Causon 22/07/2019

5 minute read

Read the article

Contact us

News & blog

Read the news & blog

Capita PLC Head Office: The Copyright Building, 30 Berners Street, London, W1T 3LR

Registered in England No. 01336850. Part of Capita plc.
© Copyright Capita PLC 2019