Surabhi V, Vijayalakshmi P, Steffina Lily, Jayanthan Ra V
Biomedical Engineering, SSN College of Engineering, Chennai, India-603110.
Annu Int Conf IEEE Eng Med Biol Soc. 2009;2009:2608-11. doi: 10.1109/IEMBS.2009.5335322.
Dysarthria is a neuromotor impairment of speech that affects one or more of the speech sub-systems. It is reflected in the acoustic characteristics of the phonemes as deviations from their healthy counterparts. In the current work, the deviations associated with laryngeal dysfunctions are analysed in order to assess and quantify parameters that will help evaluate dysarthria. Perturbation measures, pitch period statistics and Pitch Variation Index (PVI) are computed for the assessment of laryngeal dysfunctions of dysarthric speakers. The assessments were performed on the Nemours database of dysarthric speech and compared with normal speakers available in the TIMIT speech corpus. The results were correlated with Frenchay Dysarthria Assessment (FDA) scores. The analysis resulted in a technique to predict the degree of severity of dysarthria and illustrate the multi-causal nature of the disorder.
构音障碍是一种影响一个或多个言语子系统的言语神经运动障碍。它反映在音素的声学特征上,表现为与健康音素的偏差。在当前的研究中,分析与喉部功能障碍相关的偏差,以便评估和量化有助于评估构音障碍的参数。计算扰动测量、基音周期统计和基音变化指数(PVI),以评估构音障碍患者的喉部功能障碍。评估是在Nemours构音障碍语音数据库上进行的,并与TIMIT语音语料库中的正常说话者进行比较。结果与Frenchay构音障碍评估(FDA)分数相关。该分析产生了一种预测构音障碍严重程度的技术,并说明了该障碍的多因果性质。