Speaker Representation Learning using Global Context Guided Channel and Time-Frequency Transformations

TL;DR

This paper introduces a novel global context guided transformation approach for speaker representation learning, significantly improving speaker verification accuracy by modeling long-range dependencies with minimal additional computational cost.

Contribution

The study proposes a new global context guided channel and time-frequency transformation module that enhances speaker representations in CNN models, outperforming existing methods like Squeeze&Excitation.

Findings

Equal Error Rate reduced from 4.56% to 3.07%.

Achieved 32.68% relative EER reduction.

Improved DCF score by 27.28%.

Abstract

In this study, we propose the global context guided channel and time-frequency transformations to model the long-range, non-local time-frequency dependencies and channel variances in speaker representations. We use the global context information to enhance important channels and recalibrate salient time-frequency locations by computing the similarity between the global context and local features. The proposed modules, together with a popular ResNet based model, are evaluated on the VoxCeleb1 dataset, which is a large scale speaker verification corpus collected in the wild. This lightweight block can be easily incorporated into a CNN model with little additional computational costs and effectively improves the speaker verification performance compared to the baseline ResNet-LDE model and the Squeeze&Excitation block by a large margin. Detailed ablation studies are also performed to analyze various factors that may impact the performance of the proposed modules. We find that by employing the proposed L2-tf-GTFC transformation block, the Equal Error Rate decreases from 4.56% to 3.07%, a relative 32.68% reduction, and a relative 27.28% improvement in terms of the DCF score. The results indicate that our proposed global context guided transformation modules can efficiently improve the learned speaker representations by achieving time-frequency and channel-wise feature recalibration.