UNSW Associate Professor Julien Epps' expertise in vocal analysis using machine learning will be applied to the five-year study of how Lifeline helps crisis callers.
When the phones started ringing at Lifeline in 1963, no one could have imagined the reach and benefit this not-for-profit organisation would have on the mental health of hundreds of thousands of Australians.
Today about 1 million calls each year are made to Lifeline 13 11 14, the national telephone helpline. Research studies have estimated that between 3 and 5 per cent of the Australian population has called Lifeline at some point.
But what is surprising is that in the half-century of Lifeline's its operation, few studies have been undertaken to identify the outcomes achieved for callers to the service, or whether people using the service derived help appropriate to their needs.
The studies that have been undertaken have been small-scale, unpublished and have not used validated measures of outcomes related to the purpose of the service.
A grant from the National Health and Medical Research Council (NHMRC) is about to change all that.
More than $1.1 million has been set aside for a five-year study to enable a multi-institutional, multi-disciplined analysis of Lifeline’s crisis support services – telephone and online – and the impact they make for those who use them.
One of the academics involved is UNSW Sydney Faculty of Engineering’s Deputy Head of School (Education), Associate Professor Julien Epps of the School of Electrical Engineering and Telecommunications.
A/Professor Epps and his team will be looking at how machine learning can be used to analyse the vocal tone of people calling in to identify the kind of help they need.
"My team will lead the use of artificial intelligence methods to automatically identify different types of help-seekers based on their vocal qualities," A/Professor Epps says, adding that the AI will also be able to examine written communication in cases of online chat and SMS text.
"The analysis of acoustic and linguistic information from the speech of crisis callers is a highly novel research area, where there is significant potential for new technology to contribute."
While this is still somewhat speculative, A/Professor Epps expects machine learning could be ever-present, listening in to calls to triage them while contributing to Lifeline’s long-term strategies for supporting help-seekers.
"The crisis supporter will probably always be the first responder, but the use of machine learning could be a cue to get other specialists involved part-way through the call, or for example, help assess how many distressing calls a crisis supporter has had to handle," he says.
A/Professor Epps is no stranger to using vocal recognition technology to analyse speech patterns of people experiencing depression.
He and his colleagues have analysed voice samples of people who are depressed and compared them with those of people who are not.
"We focused exclusively on the acoustic qualities of the voice," A/Professor Epps says.
"We listened to the way it sounded, the timbre, the prosody – by which I mean the intonation and changes in energy – as a person speaks.
"The results up until now have been quite striking. There definitely appear to be tell-tale characteristics of a depressed person’s speech, such as flatness in tone, low energy and lack of expressiveness, which can be automatically extracted using signal processing methods."
But the tests so far have been mainly in controlled laboratory conditions with high-end audio equipment. Whether the same patterns can be detected using the audio conditions of a telephone call is a research challenge, but A/Professor Epps’ experience working with a smartphone app startup doing just this makes him confident that machine learning in the call-centre conditions will be up to the task.
Academics from eight Australian universities and one in the US will be contributing to the study, with backgrounds in psychiatry, psychology, sociology and engineering.
Chief Investigator leading the study is University of Canberra’s Professor Debra Rickwood, who developed the idea after doing some evaluation work with staff at Lifeline.
"Lifeline has moved into the digital age and offers crisis support via online chat and soon via SMS text messaging," Professor Rickwood says.
"Yet, despite increasingly widespread reliance on Lifeline, little research has identified the types of help-seekers that such crisis services are expected to support, nor the outcomes expected to be achieved."
Both she and Professor Epps have a positive outlook on what the research will achieve.
"We expect this research to enable Lifeline – and other crisis supports internationally – to be able to better meet the needs of community members in crisis, by using advanced technology and research methods," Professor Rickwood says.
A/Professor Epps adds: "The project will directly impact help-seekers by ensuring they are provided the most appropriate crisis support at the time they need it most."
Lifeline Australia executive director Alan Woodward says measuring the impact of the group in a rigorous and scientific way can only help the people who come to use it.
"In all ways, the focus on outcomes and the monitoring service performance is a way of putting the person first – something that is deep within the tradition and culture of Lifeline," he says.
