arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2204.01005eess.AScs.AI
收藏

用于说话人确认的频率和多尺度选择性核心注意力

Frequency and Multi-Scale Selective Kernel Attention for Speaker Verification

Seoul National University(首尔国立大学);Naver Corporation(Naver公司)

Sung Hwan Mun, Jee-weon Jung, Min Hyun Han, Nam Soo Kim

摘要:

大多数最新的说话人确认架构采用多尺度处理和频率通道注意机制。这些模型的卷积层通常具有固定的核大小,例如,3或5。在这项研究中,我们利用选择性核心注意力(SKA)机制进一步促进了这一研究。SKA机制允许每个卷积层以数据驱动的方式自适应地选择内核大小。它是基于一个注意机制,利用频率和信道域。我们首先将现有的SKA模块应用于我们的基线。然后,我们提出了两种SKA变体,其中第一种变体应用于ECAPA-TDNN模型的前面,另一种变体与Res2net骨干块相结合。通过大量的实验,我们证明了我们提出的两个SKA变体一致地提高了性能,并且在三种不同的评估协议上进行测试时是互补的。

英文摘要:

The majority of recent state-of-the-art speaker verification architectures adopt multi-scale processing and frequency-channel attention mechanisms. Convolutional layers of these models typically have a fixed kernel size, e.g., 3 or 5. In this study, we further contribute to this line of research utilising a selective kernel attention (SKA) mechanism. The SKA mechanism allows each convolutional layer to adaptively select the kernel size in a data-driven fashion. It is based on an attention mechanism which exploits both frequency and channel domain. We first apply existing SKA module to our baseline. Then we propose two SKA variants where the first variant is applied in front of the ECAPA-TDNN model and the other is combined with the Res2net backbone block. Through extensive experiments, we demonstrate that our two proposed SKA variants consistently improves the performance and are complementary when tested on three different evaluation protocols.

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。

↑