This paper argues that training Generative Adversarial Networks (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 processes emerge in a deep convolutional architecture. Acquisition of speech has recently been modeled as a dependency between latent space and data generated by GANs in Beguš (2020b), who models learning of a simple local allophonic distribution. We extend this approach to test learning of local and non-local phonological processes that include approximations of morphological processes. We further parallel outputs of the model to results of a behavioral experiment where human subjects are trained on the data used for training the GAN network. Four main conclusions emerge: (i) the networks provide useful information for computational models of speech acquisition even if trained on a comparatively small dataset of an artificial grammar learning experiment; (ii) local processes are easier to learn than non-local processes, which matches both behavioral data in human subjects and typology in the world's languages. This paper also proposes (iii) how we can actively observe the network's progress in learning and explore the effect of training steps on learning representations by keeping latent space constant across different training steps. Finally, this paper shows that (iv) the network learns to encode the presence of a prefix with a single latent variable; by interpolating this variable, we can actively observe the operation of a non-local phonological process. The proposed technique for retrieving learning representations has general implications for our understanding of how GANs discretize continuous speech data and suggests that rule-like generalizations in the training data are represented as an interaction between variables in the network's latent space.

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 dependency between random space and generated speech data in the Generative Adversarial Network architecture and proposes a methodology to uncover the networks internal representations that correspond to phonetic and phonological properties. The Generative Adversarial architecture is uniquely appropriate for modeling phonetic and phonological learning because the network is trained on unannotated raw acoustic data and learning is unsupervised without any language-specific assumptions or pre-assumed levels of abstraction. A Generative Adversarial Network was trained on an allophonic distribution in English, in which voiceless stops surface as aspirated word-initially before stressed vowels, except if preceded by a sibilant [s]. The network successfully learns the allophonic alternation: the networks generated speech signal contains the conditional distribution of aspiration duration. The paper proposes a technique for establishing the networks internal representations that identifies latent variables that correspond to, for example, presence of [s] and its spectral properties. By manipulating these variables, we actively control the presence of [s] and its frication amplitude in the generated outputs. This suggests that the network learns to use latent variables as an approximation of phonetic and phonological representations. Crucially, we observe that the dependencies learned in training extend beyond the training interval, which allows for additional exploration of learning representations. The paper also discusses how the networks architecture and innovative outputs resemble and differ from linguistic behavior in language acquisition, speech disorders, and speech errors, and how well-understood dependencies in speech data can help us interpret how neural networks learn their representations.

Abstract: The intervocalic position favors voicing in stops. Yet, some languages have been reported to feature the opposite (unnatural) process of intervocalic devoicing. This paper investigates two such case studies. Pre-Berawan intervocalic *b and *g have developed into Berawan k. Pre-Kiput intervocalic *g, *ɟʝ, and *v have developed into Kiput k, cç, and f, respectively. To account for the data, we invoke Beguš’s (2018, 2019) blurring process model of sound change. The model proposes that unnatural phonology derives from a sequence of at least three phonetically motivated sound changes. We argue that the steps involved in intervocalic devoicing are (i) the intervocalic fricativization of voiced stops, (ii) devoicing of fricatives, and (iii) the occlusion of devoiced fricatives. Each of the steps is independently attested and motivated. We demonstrate that our blurring process proposal explains aspects of the historical development unaccounted for by previous approaches, and present new evidence suggesting that a single sound change could not have operated in the prehistory of Berawan. Thus, we maintain the conservative position that unnatural diachronic developments arise from sequences of natural and phonetically grounded sound changes.

Comparing artificial neural networks with outputs of neuroimaging techniques has recently seen substantial advances in (computer) vision and text-based language models. Here, we propose a framework to compare biological and artificial neural computations of spoken language representations and propose several new challenges to this paradigm. The proposed technique is based on a similar principle that underlies electroencephalography (EEG): averaging of neural (artificial or biological) activity across neurons in the time domain, and allows to compare encoding of any acoustic property in the brain and in intermediate convolutional layers of an artificial neural network. Our approach allows a direct comparison of responses to a phonetic property in the brain and in deep neural networks that requires no linear transformations between the signals. We argue that the brain stem response (cABR) and the response in intermediate convolutional layers to the exact same stimulus are highly similar without applying any transformations, and we quantify this observation. The proposed technique not only reveals similarities, but also allows for analysis of the encoding of actual acoustic properties in the two signals: we compare peak latency (i) in cABR relative to the stimulus in the brain stem and in (ii) intermediate convolutional layers relative to the input/output in deep convolutional networks. We also examine and compare the effect of prior language exposure on the peak latency in cABR and in intermediate convolutional layers. Substantial similarities in peak latency encoding between the human brain and intermediate convolutional networks emerge based on results from eight trained networks (including a replication experiment). The proposed technique can be used to compare encoding between the human brain and intermediate convolutional layers for any acoustic property and for other neuroimaging techniques.

Computational models of syntax are predominantly text-based. Here we propose that basic syntax can be modeled directly from raw speech in a fully unsupervised way. We focus on one of the most ubiquitous and elementary properties of syntax---concatenation. We introduce \textit{spontaneous concatenation}: a phenomenon where convolutional neural networks (CNNs) trained on acoustic recordings of individual words start generating outputs with two or even three words concatenated without ever accessing data with multiple words in the input. Additionally, networks trained on two words learn to embed words into novel unobserved word combinations. To our knowledge, this is a previously unreported property of CNNs trained on raw speech in the Generative Adversarial Network setting and has implications both for our understanding of how these architectures learn as well as for modeling syntax and its evolution from raw acoustic inputs.

Machine learning has been advancing dramatically over the past decade. Most strides are human-based applications due to the availability of large-scale datasets; however, opportunities are ripe to apply this technology to more deeply understand non-human communication. We detail a scientific roadmap for advancing the understanding of communication of whales that can be built further upon as a template to decipher other forms of animal and non-human communication. Sperm whales, with their highly developed neuroanatomical features, cognitive abilities, social structures, and discrete click-based encoding make for an excellent model for advanced tools that can be applied to other animals in the future. We outline the key elements required for the collection and processing of massive datasets, detecting basic communication units and language-like higher-level structures, and validating models through interactive playback experiments. The technological capabilities developed by such an undertaking hold potential for cross-applications in broader communities investigating non-human communication and behavioral research.