Computer Can Recognize Emotions in Speech
News Nov 09, 2017 | Original story from the Higher School of Economics
Spectrograms of the phrase 'Kids are talking by the door' pronounced with different emotions. Credit: The Higher School of Economics
Experts of the Faculty of Informatics, Mathematics, and Computer Science at the Higher School of Economics have created an automatic system capable of identifying emotions in the sound of a voice. Their report was presented at a major international conference - Neuroinformatics-2017.
For a long time, computers have successfully converted speech into text. However, the emotional component, which is important for conveying meaning, has been neglected. For example, for the same question 'Is everything okay?', people can answer 'Of course it is!' with different intonations: calm, provoking, cheerful, etc. And the reactions will be completely different.
Neural networks are processors connected with each other and capable of learning, analysis and synthesis. This smart system surpasses traditional algorithms in that the interaction between a person and computer becomes more interactive.
HSE researchers Anastasia Popova, Alexander Rassadin and Alexander Ponomarenko have trained a neural network to recognize eight different emotions: neutral, calm, happy, sad, angry, scared, disgusted, and surprised. In 70% of cases the computer identified the emotion correctly, say the researchers.
The researchers have transformed the sound into images - spectrograms - which allowed them to work with sound using the methods applied for image recognition. A deep learning convolutional neural network with VGG-16 architecture was used in the research.
The researchers note that the programme successfully distinguishes neutral and calm tones, while happiness and surprise are not always recognized well. Happiness is often perceived as fear and sadness, and surprise is interpreted as disgust.
This article has been republished from materials provided by the Higher School of Economics. Note: material may have been edited for length and content. For further information, please contact the cited source.
Algorithm Speeds Up Medical Image Analysis 1000 TimesNews
Medical image registration is a common technique that involves overlaying two images, such as magnetic resonance imaging (MRI) scans, to compare and analyze anatomical differences in great detail. Researchers have described a machine-learning algorithm that can register brain scans and other 3-D images more than 1,000 times more quickly using novel learning techniques.
Antarctic Worm and Machine Learning Help Identify Cerebral Palsy EarlierNews
A research team has released a study in the peer-reviewed journal BMC Bioinformatics showing that DNA methylation patterns in circulating blood cells can be used to help identify spastic cerebral palsy (CP) patients. The technique which makes use of machine learning, data science and even analysis of Antarctic worms, raises hopes for earlier targeted CP therapies.
Towards Personalized Medicine: One Type of Data is Not EnoughNews
To understand the biology of diseased organs researchers use different types of molecular data. One of the biggest computational challenges at the moment is integrating these multiple data types. A new computational method jointly analyses different types of molecular data and disentangles the sources of disease variability to guide personalized treatment.READ MORE