Disordered speech recognition is a highly challenging task. The underlying neuro-motor conditions of people with speech disorders, often compounded with co-occurring physical disabilities, lead to the difficulty in collecting large quantities of speech required for system development. This paper investigates a set of data augmentation techniques for disordered speech recognition, including vocal tract length perturbation (VTLP), tempo perturbation and speed perturbation. Both normal and disordered speech were exploited in the augmentation process. Variability among impaired speakers in both the original and augmented data was modeled using learning hidden unit contributions (LHUC) based speaker adaptive training. The final speaker adapted system constructed using the UASpeech corpus and the best augmentation approach based on speed perturbation produced up to 2.92% absolute (9.3% relative) word error rate (WER) reduction over the baseline system without data augmentation, and gave an overall WER of 26.37% on the test set containing 16 dysarthric speakers.
翻译:障碍言语识别是一项极具挑战性的任务。 语言障碍患者的基本神经运动条件,往往与身体残疾同时发生,导致难以收集系统开发所需的大量语音。本文调查了一套用于障碍言识别的数据增强技术,包括声道长扰动(VTLP)、动脉扰动和速度扰动。在增强过程中,正常和无序言语都得到了利用。原始和扩充数据中的受损语者之间的易变性是利用学习的隐性单位贡献(LHUC)语言适应性培训来模拟的。最后的演讲者根据UASpeech文组和基于快速扰动(9.3%相对)的速振动(2.92%绝对)字误差率对基线系统的减幅率进行了调整,而没有数据增强,在包含16个异常言者的测试组上给出了26.37 %的总WER。