Speaker: Alicia Lozano Díez.

Abstract: In this talk, I will present an introduction of the speaker diarization task as well as the latest approaches based on neural networks as self-attention end-to-end neural diarization (EEND) with encoder-decoder attractors (EDA) as opposed to traditional clustering-based diarization. Then, I will focus on the recently published DiaPer, and end-to-end neural diarization (EEND) system based on the Perceiver model, with cross-attention, handling a variable number of speakers and showing competitive results within the state-of-the-art, with the best published results for some of the domains.