Speech Processing for Disease - Prof. Ami Moyal, President, Afeka Tel Aviv College of Engineering

Update: 2020-09-15

Description

Imagine if voice technology could be used to diagnose diseases! This could be a reality if voice tech is used to identify non-speech sounds, such as coughs. This focus is of particular interest at the moment as the world’s governments rally resources to protect populations against COVID-19.

This is one area of focus for this week’s guest, Prof. Ami Moyal, President, Afeka Tel Aviv College of Engineering, Israel. Prof. Ami also talks about the future of voice technology and what we should be teaching children for them to be successful in the world.

Teaching is the main function of Afeka, but it does focus on research and applied research, in collaboration with industry. This stimulates a culture of creativity.

The Afeka Centre for Language Processing has been researching the use of speech processing and artificial intelligence algorithms for providing a quick and readily available pre-diagnostic assessment of COVID-19 infection, without the need for human intervention.

When it comes to a rapidly spreading virus such as COVID-19, with millions of potential carriers amongst the global population, it is essential to identify likely carriers of the virus at the early stage of infection in order to prioritize testing efforts and break the chain of transmission.

Among the earliest symptoms of COVID-19 are vocal cord edema and vocal cord infection. These affect vocal cord patterns. Afeka is modelling samples of speech, coughing and breathing, from both symptomatic and asymptomatic carriers, to compare with models taken with health subjects. Afeka is also modeling vocalization of subjects that tested negative for COVID-19, yet are exhibiting similar symptoms. This will allow the differentiation between someone who is a carrier, and someone who is not.

Prof. Ami says that people were initially hesitant about using voice commands. But this perception has changed, even for simple voice commands. In the not-so-distant-future, we will be able to communicate with any object or machine using our voice. Machines will be able to communicate with humans, using simulated voices.

Taking Afeka’s COVID-19 research a step further, Prof. Ami says he imagines one day that our voices will be analyzed continuously by our cell phones, which will notify us in real time when to go and see a doctor, because it has discovered a change in our voice that may result in an ailment.

Google, Amazon, and Facebook have defined speech recognition as a strategic goal. This will lead to major advances in the use of speech recognition. Eventually, we will be able to communicate freely with any device, whether it’s our mobile phone, refrigerator, robot, or our car.

For content producers, they must think about how they are producing content for the search algorithms of the future. Searches will be instigated through voice recognition.

Looking to the future, we need to equip children with both the skills and the knowledge to use speech recognition technology. The current generation must be able to analyze data, and be able to solve unpredictable problems.

Links from the show:

Sponsors: