The interaction of contextual, high-level linguistic knowledge and the listener’s attention to low-level phonetic details has been the subject of a large body of research in speech perception for several decades. In the current paper, I investigate this interaction by considering the specific phenomenon of word predictability and its role in modulating the listener’s attention to subphonemic details of the acoustic signal. In the first experiment, subjects are presented with a discrimination task in which target words are presented in either predictable or unpredictable sentential context and then repeated in isolation, being either acoustically identical or subtly different. The subjects more accurately discriminate contextually unpredictable words, suggesting more attention to the phonetic details of words in unpredictable contexts. In the second experiment, considering the predictions of exemplar theory, I test whether this perceptual bias could result in changes in production. In this experiment, in which subjects heard and repeated sentences, I find a significant effect of word predictability on how close the subjects’ productions were to the model’s, which suggests a role of predictability on phonetic accommodation. The results of these experiments contribute to our understanding of stored exemplars and suggest the influence of contextual predictability in sound change.

背景技术，高级语言知识的互动以及听众对低级语音细节的关注，已经成为语音感知领域数十年研究的主题。在当前的论文中，我通过考虑单词可预测性的具体现象及其在调节听众对声音信号的亚音细节方面的作用来研究这种相互作用。在第一个实验中，向受试者执行区分任务，其中目标词在可预测或不可预测的句子上下文中呈现，然后在听觉上相同或微妙不同的情况下单独重复。主题可以更准确地区分上下文不确定的内容单词，建议您在无法预测的环境中更多地注意单词的语音细节。在第二个实验中，考虑到示例性理论的预测，我测试了这种感知偏差是否会导致生产变化。在这个实验中，受试者听到并重复句子，我发现单词可预测性对受试者的发音与模型的接近程度有显着影响，这暗示了可预测性在语音适应性方面的作用。这些实验的结果有助于我们对存储的示例的理解，并暗示了上下文可预测性对声音变化的影响。