arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2207.04540eess.AScs.LGcs.SD
收藏

多频信息增强通道注意模型在说话人表征学习中的应用

Multi-Frequency Information Enhanced Channel Attention Module for Speaker Representation Learning

University of Texas at Dallas(德克萨斯大学达拉斯分校)

Mufan Sang, John H. L. Hansen

摘要:

近年来,注意机制在基于神经网络的说话人确认系统中得到了成功的应用。将Squeeze-and-Excitation块扩展到卷积神经网络中已经取得了显着的性能。然而,它使用全局平均池(GAP)来简单地沿时间和频率维度对特征进行平均,这无法在特征图中保留足够的说话人信息。在这项研究中,我们表明,GAP是一个特殊的情况下,离散余弦变换(DCT)的时间-频率域数学上只使用最低频率分量的频率分解。为了增强说话人信息提取能力,本文提出利用多频信息,设计了两个新颖有效的注意模块:单频单通道(SFSC)注意模块和多频单通道(MFSC)注意模块。在DCT的基础上,提出的注意力模块可以有效地从多个频率分量中捕获更多的说话人信息。我们在VoxCeleb数据集上进行了全面的实验,并在第一个48-UTD法医语料库上进行了探测评估。实验结果表明,我们提出的SFSC和MFSC注意力模块可以有效地生成更具鉴别力的说话人表示,并优于ResNet 34-SE和ECAPA-TDNN系统,EER分别降低了20.9%和20.2%,而无需添加额外的网络参数。

英文摘要:

Recently, attention mechanisms have been applied successfully in neural network-based speaker verification systems. Incorporating the Squeeze-and-Excitation block into convolutional neural networks has achieved remarkable performance. However, it uses global average pooling (GAP) to simply average the features along time and frequency dimensions, which is incapable of preserving sufficient speaker information in the feature maps. In this study, we show that GAP is a special case of a discrete cosine transform (DCT) on time-frequency domain mathematically using only the lowest frequency component in frequency decomposition. To strengthen the speaker information extraction ability, we propose to utilize multi-frequency information and design two novel and effective attention modules, called Single-Frequency Single-Channel (SFSC) attention module and Multi-Frequency Single-Channel (MFSC) attention module. The proposed attention modules can effectively capture more speaker information from multiple frequency components on the basis of DCT. We conduct comprehensive experiments on the VoxCeleb datasets and a probe evaluation on the 1st 48-UTD forensic corpus. Experimental results demonstrate that our proposed SFSC and MFSC attention modules can efficiently generate more discriminative speaker representations and outperform ResNet34-SE and ECAPA-TDNN systems with relative 20.9% and 20.2% reduction in EER, without adding extra network parameters.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑