Target Confusion in End-to-end Speaker Extraction: Analysis and Approaches

TL;DR

This paper analyzes the target confusion problem in end-to-end speaker extraction and proposes methods to improve speaker embedding distinguishability and correct extraction errors, leading to significant performance gains.

Contribution

It introduces a two-stage approach with metric learning for training and a post-filtering strategy for inference to address target confusion in speaker extraction.

Findings

Over 1dB SI-SDRi improvement achieved

Enhanced distinguishability of speaker embeddings

Effective correction of extraction errors

Abstract

Recently, end-to-end speaker extraction has attracted increasing attention and shown promising results. However, its performance is often inferior to that of a blind source separation (BSS) counterpart with a similar network architecture, due to the auxiliary speaker encoder may sometimes generate ambiguous speaker embeddings. Such ambiguous guidance information may confuse the separation network and hence lead to wrong extraction results, which deteriorates the overall performance. We refer to this as the target confusion problem. In this paper, we conduct an analysis of such an issue and solve it in two stages. In the training phase, we propose to integrate metric learning methods to improve the distinguishability of embeddings produced by the speaker encoder. While for inference, a novel post-filtering strategy is designed to revise the wrong results. Specifically, we first identify these confusion samples by measuring the similarities between output estimates and enrollment utterances, after which the true target sources are recovered by a subtraction operation. Experiments show that performance improvement of more than 1dB SI-SDRi can be brought, which validates the effectiveness of our methods and emphasizes the impact of the target confusion problem.