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 2106.02810eess.AScs.LG
收藏

一种基于属性对齐的语音表征学习策略

An Attribute-Aligned Strategy for Learning Speech Representation

National Tsing Hua University(国立清华大学);MOST Joint Research Center for AI Technology and All Vista Healthcare(科技部人工智能技术与全视角医疗联合研究中心)

Yu-Lin Huang, Bo-Hao Su, Y. -W. Peter Hong, Chi-Chun Lee

摘要:

语音技术的进步给我们的生活带来了便利。然而,由于语音信号包含多种个人属性,这将导致敏感信息泄漏或决策偏差,因此人们的担忧正在上升。在这项工作中,我们提出了一个属性对齐的学习策略,以获得语音表示,可以灵活地解决这些问题的属性选择机制。具体来说,我们提出了一个分层表示变分自动编码器(LR-VAE),它将语音表示分解为属性敏感的节点,以获得语音情感识别(SER)的无身份表示和说话人验证(SV)的无情感表示。我们所提出的方法实现了无身份SER的竞争力的性能和更好的性能无情感SV,相比,使用对抗学习应用于大型情感语料库,MSP-Podcast的当前最先进的方法。此外,我们提出的学习策略减少了实现多个隐私保护任务所需的模型和训练过程。

英文摘要:

Advancement in speech technology has brought convenience to our life. However, the concern is on the rise as speech signal contains multiple personal attributes, which would lead to either sensitive information leakage or bias toward decision. In this work, we propose an attribute-aligned learning strategy to derive speech representation that can flexibly address these issues by attribute-selection mechanism. Specifically, we propose a layered-representation variational autoencoder (LR-VAE), which factorizes speech representation into attribute-sensitive nodes, to derive an identity-free representation for speech emotion recognition (SER), and an emotionless representation for speaker verification (SV). Our proposed method achieves competitive performances on identity-free SER and a better performance on emotionless SV, comparing to the current state-of-the-art method of using adversarial learning applied on a large emotion corpora, the MSP-Podcast. Also, our proposed learning strategy reduces the model and training process needed to achieve multiple privacy-preserving tasks.

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。

↑