# Unsupervised Learning and Representation of Mandarin Tonal Categories by a Generative CNN

arXiv: https://arxiv.org/abs/2509.17859 · HTML: https://mlsanity.com/paper/2509.17859/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 38 references that are in the map.
- First posted on arXiv 22 Sep 2025.

## Builds on (most cited first, 11 of 11)

- [CiwGAN and fiwGAN: Encoding information in acoustic data to model lexical learning with Generative Adversarial Networks](https://mlsanity.com/paper/2006.02951/) (2020)
- [Generative Adversarial Phonology: Modeling unsupervised phonetic and phonological learning with neural networks](https://mlsanity.com/paper/2006.03965/) (2020)
- [Automatic recognition of suprasegmentals in speech](https://mlsanity.com/paper/2108.01122/) (2021)
- [Interpreting intermediate convolutional layers of generative CNNs trained on waveforms](https://mlsanity.com/paper/2104.09489/) (2021)
- [Basic syntax from speech: Spontaneous concatenation in unsupervised deep neural networks](https://mlsanity.com/paper/2305.01626/) (2023)
- [Exploring How Generative Adversarial Networks Learn Phonological Representations](https://mlsanity.com/paper/2305.12501/) (2023)
- [Tone Recognition Using Lifters and CTC](https://mlsanity.com/paper/1807.02465/) (2018)
- [Probing the phonetic and phonological knowledge of tones in Mandarin TTS models](https://mlsanity.com/paper/1912.10915/) (2019)
- [Interpreting intermediate convolutional layers in unsupervised acoustic word classification](https://mlsanity.com/paper/2110.02375/) (2021)
- [Representation Learning for Discovering Phonemic Tone Contours](https://mlsanity.com/paper/1910.08987/) (2019)
- [Automated Tone Transcription and Clustering with Tone2Vec](https://mlsanity.com/paper/2410.02324/) (2024)

## Built on by (most cited first, 1 of 1)

- [ToneCL: Contrastive Learning for Few-Shot Syllable-Level Tone Classification](https://mlsanity.com/paper/2609.24903/) (2026)

## Abstract (arXiv)

This paper outlines the methodology for modeling tonal learning in fully unsupervised models of human language acquisition. Tonal patterns are among the computationally most complex learning objectives in language. We argue that a realistic generative model of human language (ciwGAN) can learn to associate its categorical variables with Mandarin Chinese tonal categories without any labeled data. All three trained models showed statistically significant differences in F0 across categorical variables. The model trained solely on male tokens consistently encoded tone. Our results sug- gest that not only does the model learn Mandarin tonal contrasts, but it learns a system that corresponds to a stage of acquisition in human language learners. We also outline methodology for tracing tonal representations in internal convolutional layers, which shows that linguistic tools can contribute to interpretability of deep learning and can ultimately be used in neural experiments.