AI Constructs Face from Voice Clips
Researchers at the Massachusetts Institute of Technology unveiled the development of an artificial intelligence program which is capable of building up an image of a person’s face, purely from listening to audio clips of the individual. Essentially, the artificial intelligence program is provided with a small snippet of an individual’s voice and from there on analyses it, reconstructing the facial features through repeated listenings. However, given how extraordinary this technology is, there is no surprise that the artificial intelligence program is not exactly flawless and capable of reproducing a one-to-one image of an individual. On the other hand, it is a breakthrough in research and our understanding of the limits and capabilities that artificial intelligence can offer.
In a paper published this week to the, the research team gives us an insight and describes how it used trained a generative adversarial network to interpret and analyse small voice note snippets and use that information to match several biometric characteristics of the speaker. The data outputted results in matching accuracies that are much better than chance. So this program does not randomly generate a face and in fact does involve a complex algorithm to determine the facial features and structure of an individual.
However, the researchers have expressed caution for the artificial intelligence program, claiming that “Although this is a purely academic investigation, we feel that it is important to explicitly discuss in the paper a set of ethical considerations due to the potential sensitivity of facial information,” they wrote, suggesting that “any further investigation or practical use of this technology will be carefully tested to ensure that the training data is representative of the intended user population.”
With such a mind-blowing advancement in artificial intelligence, it makes you wonder if there really are any limits to artificial intelligence. There is always a use and application of artificial intelligence and with many companies now investing in AI, we will soon see it being implemented in everything.