Abstract
Commands contained in a person's speech can be detected while preserving the privacy of the speaker by applying differential noise to the original time domain speech in the frequency domain.
Creative Commons License
This work is licensed under a Creative Commons Attribution-Share Alike 4.0 License.
Recommended Citation
INC, HP, "Differentially Private Speech Collection and Recognition", Technical Disclosure Commons, (January 02, 2024)
https://www.tdcommons.org/dpubs_series/6556
COinS