Search Results for author:
Found 16 papers, 6 papers with code
CiwaGAN: Articulatory information exchange
This paper introduces CiwaGAN, a model of human spoken language acquisition that combines unsupervised articulatory modeling with an unsupervised model of information exchange through the auditory modality.
Large language models and (non-)linguistic recursion
Recursion is one of the hallmarks of human language.
Basic syntax from speech: Spontaneous concatenation in unsupervised deep neural networks
Computational models of syntax are predominantly text-based.
Large Linguistic Models: Analyzing theoretical linguistic abilities of LLMs
We show here that for the first time, the models can also generate coherent and valid formal analyses of linguistic data and illustrate the vast potential of large language models for analyses of their metalinguistic abilities.
AI-assisted coding: Experiments with GPT-4
We report several experiments using GPT-4 to generate computer code.
Approaching an unknown communication system by latent space exploration and causal inference
This paper suggests that an interpretation of the outputs of deep neural networks with causal inference methodology can be a viable strategy for approaching data about which little is known and presents another case of how deep learning can limit the hypothesis space.
Articulation GAN: Unsupervised modeling of articulatory learning
Articulatory analysis suggests that the network learns to control articulators in a similar manner to humans during speech production.
Modeling speech recognition and synthesis simultaneously: Encoding and decoding lexical and sublexical semantic information into speech with no direct access to speech data
Here, we test how encoding and decoding of lexical semantic information can emerge automatically from raw speech in unsupervised generative deep convolutional networks that combine the production and perception principles of speech.
Interpreting intermediate convolutional layers in unsupervised acoustic word classification
We propose a technique to visualize individual convolutional layers in the classifier that yields highly informative time-series data for each convolutional layer and apply it to unobserved test data.
Interpreting intermediate convolutional layers of generative CNNs trained on waveforms
This technique allows for acoustic analysis of intermediate layers that parallels the acoustic analysis of human speech data: we can extract F0, intensity, duration, formants, and other acoustic properties from intermediate layers in order to test where and how CNNs encode various types of information.
Cetacean Translation Initiative: a roadmap to deciphering the communication of sperm whales
We posit that machine learning will be the cornerstone of future collection, processing, and analysis of multimodal streams of data in animal communication studies, including bioacoustic, behavioral, biological, and environmental data.
Deep Sound Change: Deep and Iterative Learning, Convolutional Neural Networks, and Language Change
This paper proposes a framework for modeling sound change that combines deep learning and iterative learning.
Local and non-local dependency learning and emergence of rule-like representations in speech data by Deep Convolutional Generative Adversarial Networks
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.
Identity-Based Patterns in Deep Convolutional Networks: Generative Adversarial Phonology and Reduplication
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.
Generative Adversarial Phonology: Modeling unsupervised phonetic and phonological learning with neural networks
A Generative Adversarial Network was trained on an allophonic distribution in English.
CiwGAN and fiwGAN: Encoding information in acoustic data to model lexical learning with Generative Adversarial Networks
The networks trained on lexical items from TIMIT learn to encode unique information corresponding to lexical items in the form of categorical variables in their latent space.
