Word-specific tonal realizations in Mandarin

TL;DR

This study demonstrates that in Mandarin, tonal realization of words is influenced not only by phonetic and contextual factors but also significantly by word meaning, with computational models showing promising predictive power.

Contribution

It reveals that word meaning influences tonal realization in Mandarin and introduces computational models that predict pitch contours based on word embeddings.

Findings

Word type is a stronger predictor of tonal realization than other factors.

Adding meaning information improves prediction accuracy.

Token-specific embeddings predict pitch contours with 40-50% accuracy.

Abstract

The pitch contours of Mandarin two-character words are generally understood as being shaped by the underlying tones of the constituent single-character words, in interaction with articulatory constraints imposed by factors such as speech rate, co-articulation with adjacent tones, segmental make-up, and predictability. This study shows that tonal realization is also partially determined by words' meanings. We first show, on the basis of a corpus of Taiwan Mandarin spontaneous conversations, using a generalized additive regression model, and focusing on the rise-fall tone pattern, that after controlling for effects of speaker and context, word type is a stronger predictor of tonal realization than all the previously established word-form related predictors combined. Importantly, the addition of information about meaning in context improves prediction accuracy even further. We then proceed to show, using computational modeling with context-specific word embeddings, that token-specific pitch contours predict word type with 50% accuracy on held-out data, and that context-sensitive, token-specific embeddings can predict the shape of pitch contours with 40% accuracy. These accuracies, which are an order of magnitude above chance level, suggest that the relation between words' pitch contours and their meanings are sufficiently strong to be potentially functional for language users. The theoretical implications of these empirical findings are discussed.