1

Probabilistic linear discriminant analysis (PLDA) or cosine similarity has been widely used in traditional speaker verification systems as a back-end technique to measure pairwise similarities. To make better use of multiple enrollment utterances, we propose a novel attention back-end model that is applied to the utterance-level features. Specifically, we use scaled-dot self-attention and feed-forward self-attention networks as architectures that learn the intra-relationships of enrollment utterances.

speaker recognition, audio-visual, lip biometrics, deep learning, visual speech.