arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2003.11982eess.AScs.SD
收藏

为说话人识别的度量学习辩护

In defence of metric learning for speaker recognition

Naver Corporation(NAVER公司)

Joon Son Chung, Jaesung Huh, Seongkyu Mun, Minjae Lee, Hee Soo Heo, Soyeon Choe, Chiheon Ham, Sunghwan Jung, Bong-Jin Lee, Icksang Han

摘要:

本文的目标是“开集”的说话人识别看不见的发言人,理想的嵌入应该能够压缩到一个紧凑的话语级表示,具有小的内部扬声器和大的扬声器间的距离的信息。说话人识别中的一个流行观点是,用分类目标训练的网络优于度量学习方法。在本文中,我们提出了一个广泛的评价最流行的损失函数的VoxCeleb数据集上的说话人识别。我们证明,与基于分类的损失相比,香草三重损失显示出有竞争力的性能,并且用我们提出的度量学习目标训练的那些损失优于最先进的方法。

英文摘要:

The objective of this paper is 'open-set' speaker recognition of unseen speakers, where ideal embeddings should be able to condense information into a compact utterance-level representation that has small intra-speaker and large inter-speaker distance. A popular belief in speaker recognition is that networks trained with classification objectives outperform metric learning methods. In this paper, we present an extensive evaluation of most popular loss functions for speaker recognition on the VoxCeleb dataset. We demonstrate that the vanilla triplet loss shows competitive performance compared to classification-based losses, and those trained with our proposed metric learning objective outperform state-of-the-art methods.

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。

↑