iTnews

RMIT is teaching robots to understand human emotions

By Matt Johnston on Jan 25, 2019 10:56AM
RMIT is teaching robots to understand human emotions

Centrelink’s call centre bots might need stress leave.

Robots’ understanding of human speech can be a bit hit and miss at the best of times, but a team of researchers at RMIT University are hoping to give machines a better grasp on the emotional aspect of language.

“There’s always an emotional context when we talk to people and we understand it, but machines don’t understand this,” project lead Associate Professor Margaret Lech said.

“When we call an automatic call centre, for example, people get very frustrated because they talk to the machine and it does not understand that they are sad, they are anxious, that they want things to be done quickly.”

Lech said robots’ inability to pick up on subtle shifts in tone, volume and speed that convey emotion compound users’ frustration with machines in a variety of industries.

She and her team from RMIT’s School of Engineering have spent 11 years working on machine learning techniques to allow technology to understand human emotions from speech signals and analyse or predict patterns of emotional interactions in human conversations.

Voice-activated devices equipped with these capabilities would thus be able to understand both the semantic and emotional contents of speech to provide more appropriate responses.

So far the machine learning tool can pick up on seven human emotions: anger, boredom, disgust, fear, happiness, sadness, and also emotional neutrality.

Emotion recognition could result in more varied applications for voice recognition technology, and enhance users’ experiences with those services, Lech said.

“People will accept machines more, they will trust machines, they will have the feeling that the machine really understands them and can help them better.

“People, especially the elderly, will not be so reluctant to use automatic call centres. Then we can employ machines, for example, robots as companions.

“An older person may like actually talking to a machine and hear that the machine can laugh with her, can sympathise, and understand her feelings. It could also be good if used for kids’ toys. Children will interact with robotic toys that can talk emotionally, so children will learn more about emotions.”

Now we just have to wait for platforms like Spotify and Netflix to adopt the technology to suggest things we’re actually in the mood to play.

Got a news tip for our journalists? Share it with us anonymously here.
Copyright © iTnews.com.au . All rights reserved.
Tags:
call centre machine learning rmit software

Partner Content

Tackling cybersecurity in 2021
Partner Content Tackling cybersecurity in 2021
Preventing cybercrime in the world of forex trading
Promoted Content Preventing cybercrime in the world of forex trading
As Australian companies lean more heavily on the cloud, edge security is finding its stride
Partner Content As Australian companies lean more heavily on the cloud, edge security is finding its stride
Putting cyber security basics in place
Partner Content Putting cyber security basics in place

Sponsored Whitepapers

The top 5 tech trends to deliver business outcomes
The top 5 tech trends to deliver business outcomes
10 reasons why businesses need to invest in cloud security training
10 reasons why businesses need to invest in cloud security training
Your guide to application security solutions
Your guide to application security solutions
State of Software Security: Open Source Edition
State of Software Security: Open Source Edition
Five questions to ask before you upgrade to a SIEM solution
Five questions to ask before you upgrade to a SIEM solution

Events

  • On-Demand Webinar: How Poly and Microsoft are Embracing Future Work Environments
  • [iTnews and Micro Focus] Navigating the cloud modernisation minefield
By Matt Johnston
Jan 25 2019
10:56AM
0 Comments

Related Articles

  • RMIT leans on big data for online shift
  • Transport for NSW trials machine learning to detect crash blackspots
  • Beyond Bank modernises its contact centre environment
  • BlueScope Steel ramps up machine learning use
Share on Twitter Share on Facebook Share on LinkedIn Share on Whatsapp Email A Friend

Most Read Articles

TPG Telecom to start enticing NBN customers to move

TPG Telecom to start enticing NBN customers to move

Infosys scores another $40m for Centrelink payments engine build

Infosys scores another $40m for Centrelink payments engine build

Bosch, Microsoft join forces to develop vehicle software platform

Bosch, Microsoft join forces to develop vehicle software platform

Telstra InfraCo opens up telco's own fibre network

Telstra InfraCo opens up telco's own fibre network

You must be a registered member of iTnews to post a comment.
Log In | Register
All rights reserved. This material may not be published, broadcast, rewritten or redistributed in any form without prior authorisation.
Your use of this website constitutes acceptance of nextmedia's Privacy Policy and Terms & Conditions.