VOXLET

Challenge

The world is awash with electronic devices equipped with microphones and capable of recording speech. Add in biometric recognition, emotional screening, and similar audio analysis technology, and you have a context in which it has become very difficult to speak anonymously. This not only threatens individual privacy – particularly in places where censorship or retaliation are a concern – it is also of obvious concern for sensitive intelligence operations where the ability to speak anonymously can mean the difference between life and death.

While many voice obfuscation solutions already exist, thus far none of these solutions work in real-time, nor are they secure in settings where guarantees of user privacy and prevention of inference attacks are essential for user safety.

Solution

To meet this challenge Galois, GE Aerospace, the University of Vermont, and North Point Defense are collaborating on the Intelligence Advanced Research Projects Activity (IARPA)’s Anonymous Real-Time Speech (ARTS) program, which seeks to develop new technologies for anonymizing conversational speech to help safeguard individual speakers’ identities. 

The team’s solution, Vocal Obfuscation eXpert Language Encoding Technology (VOXLET), combines learning neural network models with state-of-the-art formal privacy guarantees provided via differential privacy techniques. In addition, VOXLET will utilize novel compression techniques to enable system use on resource-limited hardware. 

Value Add

• Real-Time Voice Change: Phoneme-level data extraction allows for near instantaneous speech transformation, making live conversations possible 
• High Quality Results: Finer-grain transformation also allows for much higher quality, and more natural, speech transformation, including multi-lingual conversations‍
• Guaranteed Security: Differential Privacy introduces targeted noise to obfuscate the speaker’s identity without compromising quality