FB pixel

Spies want to disguise voices while researchers work to detect voice spoofs

Spies want to disguise voices while researchers work to detect voice spoofs
 

A U.S. intelligence project incubator has announced it is looking for help creating anonymous real-time speech algorithms that disguise a speaker’s identity live.

Meanwhile, a pair of researchers in China say they have designed biometric code that is better than competing approaches at performing the opposite task – detecting voice spoofs.

The Intelligence Advanced Research Projects Activity agency has posted an invitation to develop code that can mask biometric identifiers in conversational speech. A proposers’ day will be held June 27.

Given the agency involved, anything that comes from the collaboration would likely be used government spycraft than anti-fraud capabilities aimed at consumers. Industry could eventually get a crack at the resulting research, however, given the multiplying electronic goods and services that operate with voice commands.

Specifically, IARPA officials want to see innovations that defeats threats to privacy including speaker identification, human evaluation of static traits and automated classification of dynamic traits.

The best efforts will hide identity while delivering natural-sounding conversation.

It would be interesting to see what might come of such an anonymizer meeting a voice-spoofing detector like the one described in a new paper.

A pair of researchers at Zhengzhou University say most voice biometric spoof detection algorithms examine “the physical features of speech” to do their work. They say they can determine a speaker’s gender, age and mouth shape by examining a “large number” of physiological features associated with a human face.

The physiological is combined with the physical and a densely connected convolutional neural network to spot spoofing.

They claim that, in the ASVspoof 2019 logical access scenario, their presentation attack detection algorithm improves the tandem decision cost function and equal error rate by 5 percent and 7 percent when compared to other options available.

Article Topics

 |   |   |   |   | 

Latest Biometrics News

 

UK school reprimanded by ICO for using facial recognition without DPIA

A school in Chelmsford, Essex, has been reprimanded by the Information Commissioner’s Office (ICO) for the unlawful implementation of facial…

 

Tech5 introduces flexible biometric template protection for its ABIS

Tech5 has developed biometric template protection technology that it says meets the criteria set out in the ISO/IEC 30136 standard….

 

Maza streamlines KYC with Regula biometric and document verification

Regula has integrated its document and biometric verification system into Maza Financial, a fintech company based in the United States,…

 

More ballparks to get biometric entry through MLB’s Go-Ahead Entry

Major League Baseball continues to grow its facial recognition entry program with biometrics from NEC. An article in Sports Business…

 

Inrupt enters growing digital wallet market with pitch from WWW inventor

Inrupt has launched a digital wallet, which comes with a notable endorsement from an internet pioneer. A press release says…

 

OIX calls on new UK government to accelerate digital ID rollout

The UK should work toward a digital wallet strategy, provide clarity on how ID will work across the public and…

Comments

Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.

Most Read This Week

Featured Company

Biometrics Insight, Opinion

Digital ID In-Depth

Biometrics White Papers

Biometrics Events