12.7 C
London
Saturday, October 1, 2022

Two computer scientists explain how to recognize a deepfake

Must read

RBI has no fixed dollar: rupee exchange rate: Shaktikanta Das

The forex reserve adequacy aspect is always kept in mind while: RBI intervenes in the forex market, says RBI governor. The Indian...

Abbott and O’Rourke spar over migrant bus transport, weapons and power grid failure in Texas governor’s debate

Texas Governor Greg Abbott and Democratic challenger Beto O'Rourke repeatedly clashed Friday night on issues ranging from immigration to guns in the state's lone...

Tesla’s robot is now a real robot, not just a man in a suit • londonbusinessblog.com

Tesla CEO Elon Musk started his Tesla AI Day 2022 with a fast-paced level of expectations — “we've come a long way” — then...

Indian market regulator tightens IPO disclosure standards • londonbusinessblog.com

India's market regulator has tightened disclosure standards for companies seeking an initial public offering following the lackluster performance of more than half a dozen...
Shreya Christinahttps://londonbusinessblog.com
Shreya has been with londonbusinessblog.com for 3 years, writing copy for client websites, blog posts, EDMs and other mediums to engage readers and encourage action. By collaborating with clients, our SEO manager and the wider londonbusinessblog.com team, Shreya seeks to understand an audience before creating memorable, persuasive copy.

We did the opposite. By reversing many of these same techniques, we were able to get an approximation of a speaker’s vocal tract during a speech segment. This allowed us to effectively look into the anatomy of the speaker who created the audio sample.

From here on, we assumed that deepfake audio samples would not be limited by the same anatomical limitations that humans have. In other words, the analysis of deepfak audio samples simulated shapes of the vocal tract not found in humans.

Our test results not only confirmed our hypothesis, but also revealed something interesting. When extracting vocal tract estimates from deepfake audio, we found that the estimates were often comically incorrect. For example, it was common for deepfake audio to result in vocal channels with the same relative diameter and consistency as a drinking straw, as opposed to human vocal channels, which are much wider and more variable in shape.

This realization shows that deepfake audio, even when convincing to human listeners, is far from distinguishable from human-generated speech. By estimating the anatomy responsible for creating the perceived speech, it is possible to identify whether the audio was generated by a person or a computer.

Why this is important?

Today’s world is defined by the digital exchange of media and information. Everything from news to entertainment to conversations with loved ones usually happens through digital exchanges. Even in their infancy, deepfake video and audio undermine people’s trust in these exchanges, effectively limiting their usefulness.

If the digital world is to remain a critical source of information in people’s lives, effective and secure techniques for determining the source of an audio clip are critical.


Logan Blue is a Ph.D. student in computer and information science and engineering at the University of Florida. Patrick Traynor is a professor of computer and information science and engineering at the University of Florida.

This article was republished from The conversation under a Creative Commons license. Read the original article.

More articles

LEAVE A REPLY

Please enter your comment!
Please enter your name here

Latest article

RBI has no fixed dollar: rupee exchange rate: Shaktikanta Das

The forex reserve adequacy aspect is always kept in mind while: RBI intervenes in the forex market, says RBI governor. The Indian...

Abbott and O’Rourke spar over migrant bus transport, weapons and power grid failure in Texas governor’s debate

Texas Governor Greg Abbott and Democratic challenger Beto O'Rourke repeatedly clashed Friday night on issues ranging from immigration to guns in the state's lone...

Tesla’s robot is now a real robot, not just a man in a suit • londonbusinessblog.com

Tesla CEO Elon Musk started his Tesla AI Day 2022 with a fast-paced level of expectations — “we've come a long way” — then...

Indian market regulator tightens IPO disclosure standards • londonbusinessblog.com

India's market regulator has tightened disclosure standards for companies seeking an initial public offering following the lackluster performance of more than half a dozen...

Tesla now has 160,000 active fully self-driving cars and one Dojo supercomputer

Tesla's Optimus robot prototype wasn't the only thing the company shared at its AI Day presentation Friday night. Autopilot director Ashok Elluswamy took...