In this paper, we explore vector quantization for acoustic unit discovery. Leveraging
unlabelled data, we aim to learn discrete representations of speech that separate phonetic …

For our submission to the ZeroSpeech 2019 challenge, we apply discrete latent-variable
neural networks to unlabelled speech and use the discovered units for speech synthesis …

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 …

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 …

In the first year of life, infants' speech perception becomes attuned to the sounds of their
native language. This process of early phonetic learning has traditionally been framed as …

This paper models unsupervised learning of an identity-based pattern (or copying) in
speech called reduplication from raw continuous data with deep convolutional neural …

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 …

This paper explores how Generative Adversarial Networks (GANs) learn representations of
phonological phenomena. We analyze how GANs encode contrastive and non-contrastive …

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 …

This paper models phonetic and phonological learning as a dependency between random
space and generated speech data in the Generative Adversarial Neural network architecture …