Embodiments of the invention are directed to systems and methods for authentication using audio filtering. In some embodiments, an original audio segment such as a voice segment may be received. The received original audio segment may be modified using a first predetermined algorithm. The modified audio segment may be sent to an authentication server. At the authentication server, the modified audio segment may be reconstructed into the original audio segment using a second predetermined algorithm. The client device may be authenticated for a transaction based at least in part on the reconstructed original audio segment.