Ziegler Wolfram, Aichert Ingrid
EKN - Clinical Neuropsychology Research Group, Clinic for Neuropsychology, City Hospital, Munich, Germany.
EKN - Clinical Neuropsychology Research Group, Clinic for Neuropsychology, City Hospital, Munich, Germany.
Cortex. 2015 Aug;69:24-39. doi: 10.1016/j.cortex.2015.04.001. Epub 2015 Apr 15.
According to intuitive concepts, 'ease of articulation' is influenced by factors like word length or the presence of consonant clusters in an utterance. Imaging studies of speech motor control use these factors to systematically tax the speech motor system. Evidence from apraxia of speech, a disorder supposed to result from speech motor planning impairment after lesions to speech motor centers in the left hemisphere, supports the relevance of these and other factors in disordered speech planning and the genesis of apraxic speech errors. Yet, there is no unified account of the structural properties rendering a word easy or difficult to pronounce.
To model the motor planning demands of word articulation by a nonlinear regression model trained to predict the likelihood of accurate word production in apraxia of speech.
We used a tree-structure model in which vocal tract gestures are embedded in hierarchically nested prosodic domains to derive a recursive set of terms for the computation of the likelihood of accurate word production. The model was trained with accuracy data from a set of 136 words averaged over 66 samples from apraxic speakers. In a second step, the model coefficients were used to predict a test dataset of accuracy values for 96 new words, averaged over 120 samples produced by a different group of apraxic speakers.
Accurate modeling of the first dataset was achieved in the training study (R(2)adj = .71). In the cross-validation, the test dataset was predicted with a high accuracy as well (R(2)adj = .67). The model shape, as reflected by the coefficient estimates, was consistent with current phonetic theories and with clinical evidence. In accordance with phonetic and psycholinguistic work, a strong influence of word stress on articulation errors was found.
The proposed model provides a unified and transparent account of the motor planning requirements of word articulation.
根据直观概念，“发音难易程度”受诸如单词长度或话语中辅音连缀的存在等因素影响。言语运动控制的影像学研究利用这些因素来系统地对言语运动系统进行测试。来自言语失用症的证据支持了这些及其他因素在言语计划紊乱和失用性言语错误发生中的相关性，言语失用症是一种被认为由左半球言语运动中枢受损后言语运动计划障碍导致的疾病。然而，对于使一个单词发音容易或困难的结构特性，尚无统一的解释。
通过训练以预测言语失用症中准确单词产出可能性的非线性回归模型，对单词发音的运动计划需求进行建模。
我们使用了一种树形结构模型，其中声道手势嵌入在分层嵌套的韵律域中，以导出一组递归项来计算准确单词产出的可能性。该模型使用来自一组136个单词的准确性数据进行训练，这些数据是对66名失用症患者的样本进行平均得到的。第二步，使用模型系数预测96个新单词的准确性值测试数据集，这些数据是对另一组失用症患者产生的120个样本进行平均得到的。
在训练研究中实现了对第一个数据集的准确建模（调整后R² = 0.71）。在交叉验证中，测试数据集也得到了较高的预测准确率（调整后R² = 0.67）。由系数估计反映的模型形状与当前语音理论和临床证据一致。根据语音学和心理语言学研究，发现单词重音对发音错误有很大影响。
所提出的模型为单词发音的运动计划要求提供了一个统一且透明的解释。
Zotero 插件