Unsupervised segmentation and clustering of unlabelled speech are core problems in zero-
resource speech processing. Most approaches lie at methodological extremes: some use …

In this work, we propose a hierarchical subspace model for acoustic unit discovery. In this
approach, we frame the task as one of learning embeddings on a low-dimensional phonetic …

Latent Dirichlet allocation (LDA) is widely used for unsupervised topic modelling on sets of
documents. No temporal information is used in the model. However, there is often a …

This study addresses unsupervised subword modeling, ie, learning acoustic feature
representations that can distinguish between subword units of a language. We propose a …

From an early age, infants show an innate ability to infer linguistic structures from the speech
signal long before they learn to read and write. In contrast, modern speech recognition …

We experiment with unsupervised methods for deriving and clustering symbolic
representations of speech, working towards speech-to-speech translation for languages …

In this paper we describe our submission to the Zerospeech 2020 challenge, where the
participants are required to discover latent representations from unannotated speech, and to …

Lucas Ondel – Ph. D. candidate Page 1 Lucas Ondel Ph. D. candidate +420 777 234 742
lucas.ondel@gmail.com Education 2012 2020 Ph.D. in Automatic Speech Recognition, Brno …