Intelligence Value
The ARTS program aims to develop novel algorithms that will modify spontaneous speech in real-time to protect an individual’s privacy.
Summary
Countless electronics in modern life, like smart phones, digital assistants, televisions, remote controls, and even appliances, have microphones that are always listening for speech signals, using voice driven technologies to interact with people. But recorded speech contains a wealth of personal, sensitive information that can be exploited by privacy threats such as biometric recognition, background profiling, and emotional screening; a person’s speech can reveal not only their identity, but also static traits, such as dialect, gender, and age, as well as dynamic traits, such as fear, stress, and anger. The ARTS program aims to develop new methods that will anonymize conversational speech without degrading usability. The capabilities developed in this program will overcome threats to privacy such as speaker identification software, human evaluation of static traits, and automated classification of dynamic traits. The program desires novel software-based systems suitable for conversations, with the transformed speech that is understandable, sounds natural, and operates in real-time.
PROPOSERS' DAY INFORMATION:
ARTS Proposers' Day Registration Site
