6 papers
One TTS Alignment To Rule Them All
Rohan Badlani, Adrian Łancucki, Kevin J. Shih +3
Speech-to-text alignment is a critical component of neural textto-speech (TTS) models. Autoregressive TTS models typically use an attention mechanism to learn these alignments on-l…
Named Entity Recognition and Linking Augmented with Large-Scale Structured Data
Paweł Rychlikowski, Bartłomiej Najdecki, Adrian Łańcucki +1
In this paper we describe our submissions to the 2nd and 3rd SlavNER Shared Tasks held at BSNLP 2019 and BSNLP 2021, respectively. The tasks focused on the analysis of Named Entiti…
A Convolutional Deep Markov Model for Unsupervised Speech Representation Learning
Sameer Khurana, Antoine Laurent, Wei-Ning Hsu +4
Probabilistic Latent Variable Models (LVMs) provide an alternative to self-supervised learning approaches for linguistic representation learning from speech. LVMs admit an intuitiv…
Towards Using Context-Dependent Symbols in CTC Without State-Tying Decision Trees
Jan Chorowski, Adrian Lancucki, Bartosz Kostka +1
Deep neural acoustic models benefit from context-dependent (CD) modeling of output symbols. We consider direct training of CTC networks with CD outputs, and identify two issues. Th…
Efficient Purely Convolutional Text Encoding
Szymon Malik, Adrian Lancucki, Jan Chorowski
In this work, we focus on a lightweight convolutional architecture that creates fixed-size vector embeddings of sentences. Such representations are useful for building NLP systems,…
A Talker Ensemble: the University of Wrocław's Entry to the NIPS 2017 Conversational Intelligence Challenge
Jan Chorowski, Adrian Łańcucki, Szymon Malik +3
We present Poetwannabe, a chatbot submitted by the University of Wrocław to the NIPS 2017 Conversational Intelligence Challenge, in which it ranked first ex-aequo. It is able to co…