The unsettling algorithm behind Microsoft’s VALL-E artificial intelligence can replicate any person’s voice after just three seconds of hearing them speak.
Thanks to a disturbing new AI named VALL-E, your voice might be digitally cloned and used to mimic you.
VALL-E Can Replicate Any Human Voice
With just three seconds of audio, an artificial intelligence system has been developed that can replicate any human voice. Then, it may be used to convert any written text into speech, allowing someone to utilize the program to speak for you.
It’s also intended to match the speaker’s emotional range and tempo, making it a highly accurate type of mimicking.
Thank goodness, the public still cannot access AI technology. According to Microsoft, who owns Meta, the neural codec language model was trained on 60,000 hours of English-language speech.
AI Can Read But Has No Emotion
Del, a videogame artist at Naughty Facebook, the company that made Last of Us, claimed that VALL-E can synthesize super-high-quality text-to-speech from the same voice using a 3-second sample of real speech.
Del said that it might have an impact on audiobooks in the future. However, a large portion of the audiobook industry relies on a lot of young voice actor talent that will surely suffer the brunt of this first. At the moment, VALL-E can just read, not necessarily PERFORM with the emotional, tonal, and pacing range of a voice actor.
On Github, where the research team has published a brief explanation of how it all works along with numerous examples of inputs and outputs, you can actually hear Vall-E in action. The voices are of varying quality; some are clearly robotic, while others sound very human.
However, it’s impressive as a sort of first-pass tech showcase. Imagine where technology will go in a year, two years or five years as systems advance and the dataset for voice training grows even more.
That being said, it obviously is a problem. The AI art generator Dall-E is being criticized for privacy and ownership issues, and the ChatGPT bot is so convincing that the New York City Department of Education just prohibited it.
Vall-E has the potential to be considerably more alarming because of the likely usage in scam marketing calls or to reinforce deep bogus films.
That may sound a bit hand-writing but as our executive editor Tyler Wilde remarked at the start of the year, this stuff isn’t going away, and it’s crucial that we understand the difficulties and govern the construction and usage of AI systems before potential problems evolve into real and really huge ones.
VALL-E has undoubtedly raised some eyebrows online. This is terrible thinking about scam callers getting their hands on this, tweeted Kevin Nash.