Search Results for author: Adrian Lancucki

Found 4 papers, 1 papers with code

A Convolutional Deep Markov Model for Unsupervised Speech Representation Learning

no code implementations3 Jun 2020 Sameer Khurana, Antoine Laurent, Wei-Ning Hsu, Jan Chorowski, Adrian Lancucki, Ricard Marxer, James Glass

Probabilistic Latent Variable Models (LVMs) provide an alternative to self-supervised learning approaches for linguistic representation learning from speech.

Representation Learning Self-Supervised Learning +1

Towards Using Context-Dependent Symbols in CTC Without State-Tying Decision Trees

no code implementations14 Jan 2019 Jan Chorowski, Adrian Lancucki, Bartosz Kostka, Michal Zapotoczny

The embedding network is trained together with the rest of the acoustic model and removes one of the last cases in which neural systems have to be bootstrapped from GMM-HMM ones.

Frame Language Modelling

Efficient Purely Convolutional Text Encoding

1 code implementation3 Aug 2018 Szymon Malik, Adrian Lancucki, Jan Chorowski

In this work, we focus on a lightweight convolutional architecture that creates fixed-size vector embeddings of sentences.

Cannot find the paper you are looking for? You can Submit a new open access paper.