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 1804.10325eess.AS
收藏

模拟构音障碍语音用于临床语音应用中的训练数据增强

Simulating dysarthric speech for training data augmentation in clinical speech applications

Yishan Jiao, Ming Tu, Visar Berisha, Julie Liss

摘要:

用于语音应用的训练机器学习算法需要大量的标记训练数据集。这对于临床应用来说是有问题的,在临床应用中,由于隐私问题或缺乏访问,获得这样的数据是非常昂贵的。因此,临床语音应用程序通常使用只有几十个扬声器的小数据集开发。在本文中,我们提出了一种模拟训练数据的临床应用的方法,通过使用对抗训练将健康语音转换为构音障碍语音。我们使用客观和主观标准来评估我们的方法的有效性。我们将转换后的样本提交给五位经验丰富的语音语言病理学家(SLP),并要求他们将样本识别为健康或构音障碍。结果表明,SLP识别转换语音构音障碍的65%的时间。在一个试点分类实验中,我们表明,通过使用模拟语音样本来平衡现有的数据集,分类精度提高了约10%后,数据增强。

英文摘要:

Training machine learning algorithms for speech applications requires large, labeled training data sets. This is problematic for clinical applications where obtaining such data is prohibitively expensive because of privacy concerns or lack of access. As a result, clinical speech applications are typically developed using small data sets with only tens of speakers. In this paper, we propose a method for simulating training data for clinical applications by transforming healthy speech to dysarthric speech using adversarial training. We evaluate the efficacy of our approach using both objective and subjective criteria. We present the transformed samples to five experienced speech-language pathologists (SLPs) and ask them to identify the samples as healthy or dysarthric. The results reveal that the SLPs identify the transformed speech as dysarthric 65% of the time. In a pilot classification experiment, we show that by using the simulated speech samples to balance an existing dataset, the classification accuracy improves by about 10% after data augmentation.

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。

↑