Convolution-Based Channel-Frequency Attention for Text-Independent Speaker Verification

TL;DR

This paper introduces a lightweight 2D convolution-based attention module, C2D-Att, that enhances speaker verification by producing fine-grained channel-frequency attention maps, leading to improved performance on VoxCeleb datasets.

Contribution

The paper proposes a novel convolution-based attention module, C2D-Att, integrated into ResNet, which efficiently captures channel and frequency information for better speaker embedding.

Findings

C2D-Att outperforms other attention methods in speaker verification.

The model achieves state-of-the-art results on VoxCeleb datasets.

The approach is robust across different model sizes.

Abstract

Deep convolutional neural networks (CNNs) have been applied to extracting speaker embeddings with significant success in speaker verification. Incorporating the attention mechanism has shown to be effective in improving the model performance. This paper presents an efficient two-dimensional convolution-based attention module, namely C2D-Att. The interaction between the convolution channel and frequency is involved in the attention calculation by lightweight convolution layers. This requires only a small number of parameters. Fine-grained attention weights are produced to represent channel and frequency-specific information. The weights are imposed on the input features to improve the representation ability for speaker modeling. The C2D-Att is integrated into a modified version of ResNet for speaker embedding extraction. Experiments are conducted on VoxCeleb datasets. The results show that C2DAtt is effective in generating discriminative attention maps and outperforms other attention methods. The proposed model shows robust performance with different scales of model size and achieves state-of-the-art results.