# Probing the phonetic and phonological knowledge of tones in Mandarin TTS models

arXiv: https://arxiv.org/abs/1912.10915 · HTML: https://mlsanity.com/paper/1912.10915/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Dec 2019.

## Built on by (most cited first, 3 of 3)

- [Improving Prosody for Unseen Texts in Speech Synthesis by Utilizing Linguistic Information and Noisy Data](https://mlsanity.com/paper/2111.07549/) (2021)
- [Unsupervised Learning and Representation of Mandarin Tonal Categories by a Generative CNN](https://mlsanity.com/paper/2509.17859/) (2025)
- [AMNet: An Acoustic Model Network for Enhanced Mandarin Speech Synthesis](https://mlsanity.com/paper/2504.09225/) (2025)

## Abstract (arXiv)

This study probes the phonetic and phonological knowledge of lexical tones in TTS models through two experiments. Controlled stimuli for testing tonal coarticulation and tone sandhi in Mandarin were fed into Tacotron 2 and WaveGlow to generate speech samples, which were subject to acoustic analysis and human evaluation. Results show that both baseline Tacotron 2 and Tacotron 2 with BERT embeddings capture the surface tonal coarticulation patterns well but fail to consistently apply the Tone-3 sandhi rule to novel sentences. Incorporating pre-trained BERT embeddings into Tacotron 2 improves the naturalness and prosody performance, and yields better generalization of Tone-3 sandhi rules to novel complex sentences, although the overall accuracy for Tone-3 sandhi was still low. Given that TTS models do capture some linguistic phenomena, it is argued that they can be used to generate and validate certain linguistic hypotheses. On the other hand, it is also suggested that linguistically informed stimuli should be included in the training and the evaluation of TTS models.