Supervised attention for speaker recognition

TL;DR

This paper introduces supervised training strategies for attention mechanisms in speaker recognition, improving the selection of informative frames and outperforming existing methods on various datasets.

Contribution

It proposes novel supervised training methods for attention in speaker recognition, enhancing frame selection and system performance.

Findings

Outperforms existing attention methods in short utterance recognition

Achieves competitive results on VoxCeleb datasets

Boosts the effectiveness of context vectors in selecting discriminative frames

Abstract

The recently proposed self-attentive pooling (SAP) has shown good performance in several speaker recognition systems. In SAP systems, the context vector is trained end-to-end together with the feature extractor, where the role of context vector is to select the most discriminative frames for speaker recognition. However, the SAP underperforms compared to the temporal average pooling (TAP) baseline in some settings, which implies that the attention is not learnt effectively in end-to-end training. To tackle this problem, we introduce strategies for training the attention mechanism in a supervised manner, which learns the context vector using classified samples. With our proposed methods, context vector can be boosted to select the most informative frames. We show that our method outperforms existing methods in various experimental settings including short utterance speaker recognition, and achieves competitive performance over the existing baselines on the VoxCeleb datasets.