Transformers achieve unrivalled performance in modelling language, but r...
The success of deep learning comes from its ability to capture the
hiera...
We investigate the performance on phoneme categorization and phoneme and...
Speech-to-text alignment is a critical component of neural textto-speech...
We present a number of low-resource approaches to the tasks of the Zero
...
In this paper we describe our submissions to the 2nd and 3rd SlavNER Sha...
We investigate the possibility of forcing a self-supervised model traine...
We present FastPitch, a fully-parallel text-to-speech model based on
Fas...
Probabilistic Latent Variable Models (LVMs) provide an alternative to
se...
In this paper we demonstrate methods for reliable and efficient training...
Deep neural acoustic models benefit from context dependent modeling of o...
In this work, we focus on a lightweight convolutional architecture that
...
We present Poetwannabe, a chatbot submitted by the University of Wrocław...
Quality of General Game Playing (GGP) matches suffers from slow
state-sw...