Figure 1 (IMAGE)

Binghamton University

Figure 1

Caption

Figure 1: Overview. (Left) Attack model imitates a voice (black). With MMMC (green), it produces distorted audio (red). MMMC model (mid) and loss terms (right) are depicted to relate with vocal I/O.

Credit

Umur Aybars Ciftci

Usage Restrictions

Credit Umur Aybars Ciftci

License

Original content

Disclaimer: AAAS and EurekAlert! are not responsible for the accuracy of news releases posted to EurekAlert! by contributing institutions or for the use of any information through the EurekAlert system.