Abstract
A growing body of literature has demonstrated that semantics can co-determine fine phonetic detail. However, the complex interplay between phonetic realization and semantics remains understudied, particularly in pitch realization. The current study investigates the tonal realization of Mandarin disyllabic words with all 20 possible combinations of two tones, as found in a corpus of Taiwan Mandarin spontaneous speech. We made use of Generalized Additive Mixed Models (GAMs) to model f0 contours as a function of a series of predictors, including gender, tonal context, tone pattern, speech rate, word position, bigram probability, speaker and word. In the GAM analysis, word and sense emerged as crucial predictors of f0 contours, with effect sizes that exceed those of tone pattern. For each word token in our dataset, we then obtained a contextualized embedding by applying the GPT-2 large language model to the context of that token in the corpus. We show that the pitch contours of word tokens can be predicted to a considerable extent from these contextualized embeddings, which approximate token-specific meanings in contexts of use. The results of our corpus study show that meaning in context and phonetic realization are far more entangled than standard linguistic theory predicts.
Abstract (translated)
越来越多的研究表明，语义可以共同决定精细的语音细节。然而，语音实现与语义之间的复杂互动关系仍然研究不足，特别是在音高的实现方面。本项研究调查了台湾普通话自然口语语料库中所有20种可能的双音节词（两个声调组合）的音高实现情况。我们利用广义加性混合模型（GAMs），将基频曲线建模为一系列预测变量的功能，包括性别、声调背景、声调模式、说话速度、单词位置、二元语法概率、说话人和具体词汇。在GAM分析中，单词和词义成为影响基频曲线的关键预测因素，其效果大小超过了声调模式的效应。对于数据集中每个词实例，我们通过将大型语言模型（如GPT-2）应用于该实例在其语料库中的上下文来获取其上下文嵌入。结果显示，这些上下文化的嵌入可以相当程度上预测单词实例的音高曲线，它们近似于在使用过程中特定词汇的具体意义。我们的语料库研究结果表明，在具体语言环境中意义与语音实现之间相互纠缠的程度远远超过标准语言理论所预测的范围。
URL
https://arxiv.org/abs/2503.23163
