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 1806.09301cs.SDeess.AS
收藏

鲁棒特征聚类在无监督语音端点检测中的应用

Robust Feature Clustering for Unsupervised Speech Activity Detection

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

Harishchandra Dubey, Abhijeet Sangwan, John H. L. Hansen

摘要:

在诸如零资源语音处理或极低资源语音语言系统的某些应用中,收集语音活动检测(SAD)注释可能是不可行的。然而,基于神经网络或其他机器学习方法的最先进的监督SAD技术需要与目标域匹配的带注释的训练数据。本文建立了一个聚类方法,完全无监督SAD有用的情况下,SAD注释不可用。所提出的方法利用哈迪根浸渍测试的递归策略分割成突出的模式的特征空间。统计倾角对失真是不变的,这为所提出的方法提供了鲁棒性。我们在NIST OpenSAD 2015和NIST OpenSAT 2017公共安全通信数据上评估了该方法。结果表明,所提出的方法优于两个组件的GMM基线。索引术语:聚类,Hartigan dip test,NIST OpenSAD,NIST OpenSAT,语音活动检测,零资源语音处理,无监督学习。

英文摘要:

In certain applications such as zero-resource speech processing or very-low resource speech-language systems, it might not be feasible to collect speech activity detection (SAD) annotations. However, the state-of-the-art supervised SAD techniques based on neural networks or other machine learning methods require annotated training data matched to the target domain. This paper establish a clustering approach for fully unsupervised SAD useful for cases where SAD annotations are not available. The proposed approach leverages Hartigan dip test in a recursive strategy for segmenting the feature space into prominent modes. Statistical dip is invariant to distortions that lends robustness to the proposed method. We evaluate the method on NIST OpenSAD 2015 and NIST OpenSAT 2017 public safety communications data. The results showed the superiority of proposed approach over the two-component GMM baseline. Index Terms: Clustering, Hartigan dip test, NIST OpenSAD, NIST OpenSAT, speech activity detection, zero-resource speech processing, unsupervised learning.

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。

↑