arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.00731eess.AScs.CL
收藏

使用概率自适应度量的无监督重复语音模式发现

Unsupervised Discovery of Recurring Speech Patterns Using Probabilistic Adaptive Metrics

Tampere University(坦佩雷大学);Aalto University(阿尔托大学)

Okko Räsänen, María Andrea Cruz Blandón

摘要:

无监督口语词项发现(UTD)旨在从声学语音数据库中发现重复出现的语音片段。解决这个问题的一个潜在方法是使用动态时间规整(DTW)从语音数据中找到良好对齐的模式。然而,用于DTW比对的初始候选片段的自动选择和其中“足够好”的比对的检测需要某种类型的预定义标准,通常可操作为信号表示之间的成对距离度量的阈值参数。在现有的UTD系统中,最佳超参数可能会因数据集而异,从而限制了它们对新语料库和真正低资源场景的适用性。在本文中,我们提出了一种新的概率方法DTW为基础的UTD命名为PDTW。在PDTW中,处理后的语料库的分布特性被用于自适应评价对齐质量,从而使系统的发现模式对,具有相似性,什么是预期的巧合。我们在零资源语音挑战2017数据集上测试PDTW,作为2020年挑战实施的一部分。结果表明,该系统在使用固定超参数的所有五种测试语言上的表现一致,在检测模式的覆盖率方面明显优于早期基于DTW的系统。

英文摘要:

Unsupervised spoken term discovery (UTD) aims at finding recurring segments of speech from a corpus of acoustic speech data. One potential approach to this problem is to use dynamic time warping (DTW) to find well-aligning patterns from the speech data. However, automatic selection of initial candidate segments for the DTW-alignment and detection of "sufficiently good" alignments among those require some type of pre-defined criteria, often operationalized as threshold parameters for pair-wise distance metrics between signal representations. In the existing UTD systems, the optimal hyperparameters may differ across datasets, limiting their applicability to new corpora and truly low-resource scenarios. In this paper, we propose a novel probabilistic approach to DTW-based UTD named as PDTW. In PDTW, distributional characteristics of the processed corpus are utilized for adaptive evaluation of alignment quality, thereby enabling systematic discovery of pattern pairs that have similarity what would be expected by coincidence. We test PDTW on Zero Resource Speech Challenge 2017 datasets as a part of 2020 implementation of the challenge. The results show that the system performs consistently on all five tested languages using fixed hyperparameters, clearly outperforming the earlier DTW-based system in terms of coverage of the detected patterns.

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。

↑