Deciphering Assamese Vowel Harmony with Featural InfoWaveGAN
Not on the map. Why?
Abstract (arXiv)
Traditional approaches for understanding phonological learning have predominantly relied on curated text data. Although insightful, such approaches limit the knowledge captured in textual representations of the spoken language. To overcome this limitation, we investigate the potential of the Featural InfoWaveGAN model to learn iterative long-distance vowel harmony using raw speech data. We focus on Assamese, a language known for its phonologically regressive and word-bound vowel harmony. We demonstrate that the model is adept at grasping the intricacies of Assamese phonotactics, particularly iterative long-distance harmony with regressive directionality. It also produced non-iterative illicit forms resembling speech errors during human language acquisition. Our statistical analysis reveals a preference for a specific [+high,+ATR] vowel as a trigger across novel items, indicative of feature learning. More data and control could improve model proficiency, contrasting the universality of learning.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 8 of its 24 references that are in the map. First posted on arXiv 9 Jul 2024.
Builds on
8 of 24 references.
References · 8
- 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
- 2016InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Netscited by 858
- 2018Adversarial Audio Synthesiscited by 222
- 2020CiwGAN and fiwGAN: Encoding information in acoustic data to model lexical learning with Generative Adversarial Networkscited by 15
- 2020Generative Adversarial Phonology: Modeling unsupervised phonetic and phonological learning with neural networkscited by 12
- 2020Identity-Based Patterns in Deep Convolutional Networks: Generative Adversarial Phonology and Reduplicationcited by 9
- 2021Interpreting intermediate convolutional layers of generative CNNs trained on waveformscited by 6
- 2023Exploring How Generative Adversarial Networks Learn Phonological Representationscited by 4
Built on by
Not cited yet.