42 citations · 157 across the 18 of their papers we have counts for
18 papers
Unsupervised Learning and Representation of Mandarin Tonal Categories by a Generative CNN
Kai Schenck, Gašper Beguš
This paper outlines the methodology for modeling tonal learning in fully unsupervised models of human language acquisition. Tonal patterns are among the computationally most comple…
Exploring the encoding of linguistic representations in the Fully-Connected Layer of generative CNNs for Speech
Bruno Ferenc Šegedin, Gasper Beguš
Interpretability work on the convolutional layers of CNNs has primarily focused on computer vision, but some studies also explore correspondences between the latent space and the o…
CiwaGAN: Articulatory information exchange
Gašper Beguš, Thomas Lu, Alan Zhou +2
Humans encode information into sounds by controlling articulators and decode information from sounds using the auditory apparatus. This paper introduces CiwaGAN, a model of human s…
Large language models and (non-)linguistic recursion
Maksymilian Dąbkowski, Gašper Beguš
Recursion is one of the hallmarks of human language. While many design features of language have been shown to exist in animal communication systems, recursion has not. Previous re…
Basic syntax from speech: Spontaneous concatenation in unsupervised deep neural networks
Gašper Beguš, Thomas Lu, Zili Wang
Computational models of syntax are predominantly text-based. Here we propose that the most basic first step in the evolution of syntax can be modeled directly from raw speech in a…
Large Linguistic Models: Investigating LLMs' metalinguistic abilities
Gašper Beguš, Maksymilian Dąbkowski, Ryan Rhodes
The performance of large language models (LLMs) has recently improved to the point where models can perform well on many language tasks. We show here that--for the first time--the…
AI-assisted coding: Experiments with GPT-4
Russell A Poldrack, Thomas Lu, Gašper Beguš
Artificial intelligence (AI) tools based on large language models have acheived human-level performance on some computer programming tasks. We report several experiments using GPT-…
Approaching an unknown communication system by latent space exploration and causal inference
Gašper Beguš, Andrej Leban, Shane Gero
This paper proposes a methodology for discovering meaningful properties in data by exploring the latent space of unsupervised deep generative models. We combine manipulation of ind…
Articulation GAN: Unsupervised modeling of articulatory learning
Gašper Beguš, Alan Zhou, Peter Wu +1
Generative deep neural networks are widely used for speech synthesis, but most existing models directly generate waveforms or spectral outputs. Humans, however, produce speech by c…
Modeling speech recognition and synthesis simultaneously: Encoding and decoding lexical and sublexical semantic information into speech with no direct access to speech data
Gašper Beguš, Alan Zhou
Human speakers encode information into raw speech which is then decoded by the listeners. This complex relationship between encoding (production) and decoding (perception) is often…
Interpreting intermediate convolutional layers in unsupervised acoustic word classification
Gašper Beguš, Alan Zhou
Understanding how deep convolutional neural networks classify data has been subject to extensive research. This paper proposes a technique to visualize and interpret intermediate l…
Cetacean Translation Initiative: a roadmap to deciphering the communication of sperm whales
Jacob Andreas, Gašper Beguš, Michael M. Bronstein +16
The past decade has witnessed a groundbreaking rise of machine learning for human language analysis, with current methods capable of automatically accurately recovering various asp…
Interpreting intermediate convolutional layers of generative CNNs trained on waveforms
Gašper Beguš, Alan Zhou
This paper presents a technique to interpret and visualize intermediate layers in generative CNNs trained on raw speech data in an unsupervised manner. We argue that averaging over…
Deep Sound Change: Deep and Iterative Learning, Convolutional Neural Networks, and Language Change
Gašper Beguš
This paper proposes a framework for modeling sound change that combines deep learning and iterative learning. Acquisition and transmission of speech is modeled by training generati…
Local and non-local dependency learning and emergence of rule-like representations in speech data by Deep Convolutional Generative Adversarial Networks
Gašper Beguš
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-li…
Identity-Based Patterns in Deep Convolutional Networks: Generative Adversarial Phonology and Reduplication
Gašper Beguš
This paper models unsupervised learning of an identity-based pattern (or copying) in speech called reduplication from raw continuous data with deep convolutional neural networks. W…
Generative Adversarial Phonology: Modeling unsupervised phonetic and phonological learning with neural networks
Gašper Beguš
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 acquisiti…
CiwGAN and fiwGAN: Encoding information in acoustic data to model lexical learning with Generative Adversarial Networks
Gašper Beguš
How can deep neural networks encode information that corresponds to words in human speech into raw acoustic data? This paper proposes two neural network architectures for modeling…