How much is a word? Predicting ease of articulation planning from apraxic speech error patterns

2015 
Abstract 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 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. Conclusions The proposed model provides a unified and transparent account of the motor planning requirements of word articulation.
    • Correction
    • Source
    • Cite
    • Save
    • Machine Reading By IdeaReader
    73
    References
    20
    Citations
    NaN
    KQI
    []