Affiliations: [a] Computer Engineering Department, Princess Sumaya University for Technology, Amman, Jordan
| [b] Computer Engineering Department, University of Jordan, Amman, Jordan
Correspondence:
[*]
Corresponding author. Amjed Al-Mousa, Computer Engineering Department, Princess Sumaya University for Technology, Amman, Jordan. E-mail: a.almousa@psut.edu.jo.
Abstract: The advent use of smart devices has enabled the emergence of many applications that facilitate user interaction through speech. However, speech reveals private and sensitive information about the user’s identity, posing several security risks. For example, a speaker’s speech can be acquired and used in speech synthesis systems to generate fake speech recordings that can be used to attack that speaker’s verification system. One solution is to anonymize the speaker’s identity from speech before using it. Existing anonymization schemes rely on using a pool of real speakers’ identities for anonymization, which may result in associating a speaker’s speech with an existing speaker. Hence, this paper investigates the use of Generative Adversarial Networks (GAN) to generate a pool of fake identities that are used for anonymization. Several GAN types were considered for this purpose, and the Conditional Tabular GAN (CTGAN) showed the best performance among all GAN types according to different metrics that measure the naturalness of the anonymized speech and its linguistic content.
