Challenging margin-based speaker embedding extractors by using the variational information bottleneck

speaker recognition, variational information bottleneck

Speaker embedding extractors are typically trained using a classification loss over the training speakers. During the last few years, the standard softmax/cross-entropy loss has been replaced by the margin-based losses, yielding significant im- provements in speaker recognition accuracy. Motivated by the fact that the margin merely reduces the logit of the target speaker during training, we consider a probabilistic framework that has a similar effect. The variational information bottle- neck provides a principled mechanism for making deterministic nodes stochastic, resulting in an implicit reduction of the pos- terior of the target speaker. We experiment with a wide range of speaker recognition benchmarks and scoring methods and re- port competitive results to those obtained with the state-of-the- art Additive Angular Margin loss.