Skip to main content

Identification of Cardiac Arrest from Triple-Zero Calls by using Multimodal Information

Primary supervisor

Lizhen Qu


  • Prof. Karen Smith
  • Dr. Resmi Nair

This project is within the scope of the project “Artificial Intelligence in carDiac arrEst” (AIDE), which was led by Ambulance Victoria (AV) in Australia, involving a team of researchers at Monash University. This AIDE project has developed an Artificial Intelligence (AI) tool to recognise potential Out-of-Hospital-Cardiac Arrest (OHCA) during the Triple Zero (000) call by using transcripts produced by Microsoft Automatic Speech Recognition service. Within the framework, the student will extend the tool to recognise OHCA effectively by using both transcripts and audio signals, and notify the call-taker of the level of probability of a cardiac arrest at the earliest possible point of recognition.

Student cohort

Single Semester
Double Semester


The goal of the thesis is to develop a novel deep learning multimodal model for recognising OHCA from triple zero calls. The key novelty is to utilize the disentangled representation learning technique, which aims to separate irrelevant audio signals from the ones for the target tasks. You are also expected to conduct extensive experiments to evaluate the new model with its competitors on real-world triple-zero calls.

Required knowledge

Preferred Skills

Students should have excellent grades in machine learning and relevant math courses. Strong programming skills are essential. Preference will be given to students who have previous practical experiences on machine learning tools such as Tensorflow, Pytorch, and ScikitLearn. Students with an interest in pursuing PhD research or careers in research are especially encouraged to apply.