How much is a word? Predicting ease of articulation planning from apraxic speech error patterns
How much is a word? Predicting ease of articulation planning from apraxic speech error patterns
复制标题
DOI：
10.1016/j.cortex.2015.04.001
复制
发表时间：
2015-08-01
期刊：
影响因子：
3.6
通讯作者：
Aichert, Ingrid
中科院分区：
文献类型：
--
作者：
Ziegler, Wolfram;Aichert, Ingrid
背景：根据直觉概念，发音的好坏受词长或发音中辅音组合等因素的影响。语音运动控制的成像研究使用这些因素来系统地对语音运动系统征税。来自语言失用症的证据支持这些因素和其他因素在语言计划障碍和失用性语言错误的发生中的相关性。语言失用症是一种被认为是由于左脑语言运动中枢受损后的语言运动计划障碍引起的疾病。目的：通过一个非线性回归模型对语音失用时准确发词的可能性进行建模。方法：我们使用一种将声道手势嵌入到分层嵌套韵律域中的树形结构模型，推导出一组递归术语集，用于计算准确发词的可能性。该模型使用来自失用说话者的平均超过66个样本的136个单词的精确度数据进行训练。在第二步中，模型系数被用来预测96个新词的准确率的测试数据集，平均超过120个样本，这些样本来自不同的失用说话者。结果：在训练研究中，第一个数据集得到了准确的建模(R-ADI(2)=.71)。在交叉验证中，测试数据集的预测精度也很高(R-adj(2)=.67)。由系数估计所反映的模型形状与当前的语音理论和临床证据是一致的。根据语音和心理语言学的研究，发现单词重音对发音错误有很强的影响。结论：该模型对单词发音的运动规划要求提供了一个统一和透明的解释。(C)2015爱思唯尔有限公司。保留所有权利。
Background: 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.Aim: 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.Method: 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.Results: Accurate modeling of the first dataset was achieved in the training study (R-adi(2) = .71). In the cross-validation, the test dataset was predicted with a high accuracy as well (R-adj(2) = .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.Conclusions: The proposed model provides a unified and transparent account of the motor planning requirements of word articulation. (C) 2015 Elsevier Ltd. All rights reserved.