arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2009.00768eess.AScs.LGeess.SP
收藏

基于全局上下文引导通道和时频变换的说话人表征学习

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

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

Wei Xia, John H. L. Hansen

摘要:

在这项研究中,我们提出了全局上下文引导的通道和时间-频率变换模型的长范围,非本地的时间-频率依赖性和通道的变化,在说话人表示。我们使用全局上下文信息来增强重要通道,并通过计算全局上下文和局部特征之间的相似性来重新校准显著的时频位置。所提出的模块,以及一个流行的基于ResNet的模型,在VoxCeleb 1数据集上进行了评估,VoxCeleb 1数据集是一个在野外收集的大规模说话人验证语料库。这个轻量级块可以很容易地合并到CNN模型中,几乎没有额外的计算成本,并且与基线ResNet-LDE模型和Squeeze&Excitation块相比,有效地提高了说话人验证性能。还进行了详细的消融研究,以分析可能影响拟议模块性能的各种因素。我们发现,通过采用所提出的L2-tf-GTFC变换块,相等错误率从4.56%降低到3.07%,相对降低32.68%,并且相对提高27.28%的DCF分数。结果表明,我们提出的全局上下文引导的变换模块可以有效地提高学习的说话人表示,实现时频和通道的功能重新校准。

英文摘要:

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.

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。

↑