Until recently, the field of speaker diarization was dominated by cascaded systems. Due to their limitations, mainly regarding overlapped speech and cumbersome pipelines, end-to-end models have gained great popularity lately. One of the most successful models is end-to-end neural diarization with encoder-decoder based attractors (EEND-EDA). In this work, we replace the EDA module with a Perceiver-based one and show its advantages over EEND-EDA; namely obtaining better performance on the largely studied Callhome dataset, finding the quantity of speakers in a conversation more accurately, and running inference on almost half of the time on long recordings. Furthermore, when exhaustively compared with other methods, our model, DiaPer, reaches remarkable performance with a very lightweight design. Besides, we perform comparisons with other works and a cascaded baseline across more than ten public wide-band datasets. Together with this publication, we release the code of DiaPer as well as models trained on public and free data.

中文翻译：

---

DiaPer：使用基于感知器的吸引器进行端到端神经二化

直到最近，说话人分类领域仍由级联系统主导。由于其局限性，主要是重叠语音和繁琐的管道，端到端模型最近非常受欢迎。最成功的模型之一是基于吸引器的编码器-解码器的端到端神经二值化（EEND-EDA）。在这项工作中，我们用基于 Perceiver 的 EDA 模块替换了 EDA 模块，并展示了其相对于 EEND-EDA 的优势；即在经过大量研究的 Callhome 数据集上获得更好的性能，更准确地找到对话中说话者的数量，并在长录音中的近一半时间上运行推理。此外，与其他方法进行详尽比较时，我们的模型 DiaPer 通过非常轻量级的设计实现了卓越的性能。此外，我们还与其他作品以及十多个公共宽带数据集的级联基线进行比较。与本出版物一起，我们发布了 DiaPer 的代码以及在公共和免费数据上训练的模型。