Speaker Identification Experiments Under Gender De-Identification
This work addresses de-identification in multimedia for privacy protection, but it is incremental as it applies existing methods to a specific scenario.
The study tested four voice modification algorithms on a speech gender recognizer to determine the pitch modification level needed for equal success and failure probabilities, assessing intensity, quality, and reversibility of changes.
The present work is based on the COST Action IC1206 for De-identification in multimedia content. It was performed to test four algorithms of voice modifications on a speech gender recognizer to find the degree of modification of pitch when the speech recognizer have the probability of success equal to the probability of failure. The purpose of this analysis is to assess the intensity of the speech tone modification, the quality, the reversibility and not-reversibility of the changes made. Keywords DeIdentification; Speech Algorithms