# The realization of tones in spontaneous spoken Taiwan Mandarin: a corpus-based survey and theory-driven computational modeling

arXiv: https://arxiv.org/abs/2503.23163 · HTML: https://mlsanity.com/paper/2503.23163/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 98 references that are in the map.
- First posted on arXiv 29 Mar 2025.

## Builds on (most cited first, 8 of 8)

- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Enriching Word Vectors with Subword Information](https://mlsanity.com/paper/1607.04606/) (2016)
- [Word-specific tonal realizations in Mandarin](https://mlsanity.com/paper/2405.07006/) (2024)
- [Modeling morphology with Linear Discriminative Learning: considerations and design choices](https://mlsanity.com/paper/2106.07936/) (2021)
- [Resolving Regular Polysemy in Named Entities](https://mlsanity.com/paper/2401.09758/) (2024)
- [Is deeper always better? Replacing linear mappings with deep learning networks in the Discriminative Lexicon Model](https://mlsanity.com/paper/2410.04259/) (2024)
- [Form and meaning co-determine the realization of tone in Taiwan Mandarin spontaneous speech: the case of T2-T3 and T3-T3 tone sandhi](https://mlsanity.com/paper/2408.15747/) (2024)
- [A corpus-based investigation of pitch contours of monosyllabic words in conversational Taiwan Mandarin](https://mlsanity.com/paper/2409.07891/) (2024)

## Built on by (most cited first, 7 of 7)

- [A new kid on the block: Distributional semantics predicts the word-specific tone signatures of monosyllabic words in conversational Taiwan Mandarin](https://mlsanity.com/paper/2511.17337/) (2025)
- [Using embeddings to predict spoken word duration and pitch in Mandarin monosyllabic words](https://mlsanity.com/paper/2607.02002/) (2026)
- [An experimental and computational study of an Estonian single-person word naming](https://mlsanity.com/paper/2509.03143/) (2025)
- [Polish phonology and morphology through the lens of distributional semantics](https://mlsanity.com/paper/2604.00174/) (2026)
- [Phonetic and semantic analyses of spoken corpora of Beijing and Taiwan Mandarin indicate that the neutral tone is a lexical tone](https://mlsanity.com/paper/2606.26360/) (2026)
- [Word meaning co-determines vowel-inherent spectral change. A corpus-based investigation of conversational Mandarin](https://mlsanity.com/paper/2607.21391/) (2026)
- [Letters hide the truth from our eyes: English homophones have meaningfully different phonetic realizations](https://mlsanity.com/paper/2608.26749/) (2026)

## Abstract (arXiv)

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.