Exploring How Generative Adversarial Networks Learn Phonological Representations
This paper explores how Generative Adversarial Networks (GANs) learn representations of phonological phenomena. We analyze how GANs encode contrastive and non-contrastive nasality in French and English vowels by applying the ciwGAN architecture (Begus 2021a). Begus claims that ciwGAN encodes linguistically meaningful representations with categorical variables in its latent space and manipulating the latent variables shows an almost one to one corresponding control of the phonological features in ciwGAN's generated outputs. However, our results show an interactive effect of latent variables on the features in the generated outputs, which suggests the learned representations in neural networks are different from the phonological representations proposed by linguists. On the other hand, ciwGAN is able to distinguish contrastive and noncontrastive features in English and French by encoding them differently. Comparing the performance of GANs learning from different languages results in a better understanding of what language specific features contribute to developing language specific phonological representations. We also discuss the role of training data frequencies in phonological feature learning.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Generative Adversarial Phonology: Modeling unsupervised phonetic and phonological learning with neural networks
Training deep neural networks on well-understood dependencies in speech data can provide new insights into how they learn internal representations. This paper argues that acquisition of speech can be modeled as a depende…
Generative Adversarial NetworkLanguage AcquisitionModeing unsupervised phonetic and phonological learning in Generative Adversarial Phonology
Speech vocoding for laboratory phonology
Using phonological speech vocoding, we propose a platform for exploring relations between phonology and speech processing, and in broader terms, for exploring relations between the abstract and physical structures of a s…
Speech Synthesistext-to-speechText to SpeechLocal and non-local dependency learning and emergence of rule-like representations in speech data by Deep Convolutional Generative Adversarial Networks
This paper argues that training GANs on local and non-local dependencies in speech data offers insights into how deep neural networks discretize continuous data and how symbolic-like rule-based morphophonological process…
Language AcquisitionEncoder-decoder models for latent phonological representations of words
We use sequence-to-sequence networks trained on sequential phonetic encoding tasks to construct compositional phonological representations of words. We show that the output of an encoder network can predict the phonetic …
Decoder