An initial investigation on optimizing tandem speaker verification and countermeasure systems using reinforcement learning
This work addresses the need for better integrated security in speaker verification systems, though it is incremental as it builds on existing tandem evaluation methods.
The paper tackled the problem of optimizing combined spoofing countermeasure and speaker verification systems by training them jointly using reinforcement learning, resulting in improved performance of the combined system compared to standard supervised learning techniques.
The spoofing countermeasure (CM) systems in automatic speaker verification (ASV) are not typically used in isolation of each other. These systems can be combined, for example, into a cascaded system where CM produces first a decision whether the input is synthetic or bona fide speech. In case the CM decides it is a bona fide sample, then the ASV system will consider it for speaker verification. End users of the system are not interested in the performance of the individual sub-modules, but instead are interested in the performance of the combined system. Such combination can be evaluated with tandem detection cost function (t-DCF) measure, yet the individual components are trained separately from each other using their own performance metrics. In this work we study training the ASV and CM components together for a better t-DCF measure by using reinforcement learning. We demonstrate that such training procedure indeed is able to improve the performance of the combined system, and does so with more reliable results than with the standard supervised learning techniques we compare against.