ECAPA-TDNN Embeddings for Speaker Diarization

TL;DR

This paper introduces the use of ECAPA-TDNN neural network embeddings for speaker diarization, demonstrating improved robustness and performance over existing methods on the AMI corpus.

Contribution

It is the first to apply ECAPA-TDNN to speaker diarization and enhances its robustness with a novel augmentation scheme.

Findings

ECAPA-TDNN embeddings outperform previous approaches

System achieves significant improvements on the AMI corpus

Robust under both close-talking and distant-talking conditions

Abstract

Learning robust speaker embeddings is a crucial step in speaker diarization. Deep neural networks can accurately capture speaker discriminative characteristics and popular deep embeddings such as x-vectors are nowadays a fundamental component of modern diarization systems. Recently, some improvements over the standard TDNN architecture used for x-vectors have been proposed. The ECAPA-TDNN model, for instance, has shown impressive performance in the speaker verification domain, thanks to a carefully designed neural model. In this work, we extend, for the first time, the use of the ECAPA-TDNN model to speaker diarization. Moreover, we improved its robustness with a powerful augmentation scheme that concatenates several contaminated versions of the same signal within the same training batch. The ECAPA-TDNN model turned out to provide robust speaker embeddings under both close-talking and distant-talking conditions. Our results on the popular AMI meeting corpus show that our system significantly outperforms recently proposed approaches.