Last year, we saw advanced lip syncing tech used to create convincing speeches from former US president Barack Obama. Today, researchers from China’s biggest search engine Baidu announced a program that can clone any voice and reuse it as it sees fit. #softwaremagic
Baidu researchers have developed an AI program that needs to hear only seconds of your voice to replicate and alter it. Basically, it can put a different accent on your voice or remodel it to sound female or male. That sounds deceptively easy, mind you. Until Baidu’s breakthrough, Adobe VoCo was able to mimic a voice after 20 minutes, not seconds, of input!
According to New Scientist, the program created one voice capable of fooling voice recognition software with 95% accuracy! The benefits of such tech are enormous. Parents could use it with their kids when they’re away, ensuring they have a soothing voice to listen to. Even better, people who have lost the ability to talk would be able to hear themselves talking again and facilitate interactions with their dear ones. Digital assistants would be able to talk in different tones instead of using the same universal voice.
However, there are potential consequences to such a program. If this technology falls into the wrong hands, the consequences could be dire. For example, it would be easy to use AI to manufacture speeches.
In the end, like all technology breakthroughs that blur the line between humans and computers, there are ethical issues to consider.