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 2003.09125eess.AScs.LG
收藏

用梯形网络改进说话人确认的嵌入提取

Improving Embedding Extraction for Speaker Verification with Ladder Network

Uber AI Labs(优步人工智能实验室)

Fei Tao, Gokhan Tur

摘要:

说话人确认是语音处理领域中一个成熟而又富有挑战性的课题,也是一个非常活跃的研究领域。最近的说话人验证(SV)系统依赖于深度神经网络来提取能够表征用户语音的高级嵌入。大多数的研究都在研究如何提高网络的区分度,以提取更好的嵌入来提高性能。然而,只有很少的研究集中在提高泛化能力。在本文中,我们提出了应用梯形网络框架的SV系统,它结合了监督和无监督的学习方式。梯形网络可以通过平衡保留/丢弃尽可能多的有用/无用信息来使系统具有更好的高层嵌入。我们在两个最先进的SV系统(d-vector和x-vector)上评估了该框架,它们可用于不同的用例。实验结果表明,该方法在不增加参数和扩充数据的情况下,最多可使性能提高10%。

英文摘要:

Speaker verification is an established yet challenging task in speech processing and a very vibrant research area. Recent speaker verification (SV) systems rely on deep neural networks to extract high-level embeddings which are able to characterize the users' voices. Most of the studies have investigated on improving the discriminability of the networks to extract better embeddings for performances improvement. However, only few research focus on improving the generalization. In this paper, we propose to apply the ladder network framework in the SV systems, which combines the supervised and unsupervised learning fashions. The ladder network can make the system to have better high-level embedding by balancing the trade-off to keep/discard as much useful/useless information as possible. We evaluated the framework on two state-of-the-art SV systems, d-vector and x-vector, which can be used for different use cases. The experiments showed that the proposed approach relatively improved the performance by 10% at most without adding parameters and augmented data.

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。

↑