Transfer learning has proven to be crucial in advancing the state of spe...
Textless spoken language processing research aims to extend the applicab...
Video recordings of speech contain correlated audio and visual informati...
This paper presents XLS-R, a large-scale model for cross-lingual speech
...
Despite their recent popularity and well known advantages, dense retriev...
Speech pre-training has primarily demonstrated efficacy on classificatio...
Pre-training on larger datasets with ever increasing model size is now a...
Self-supervised approaches for speech representation learning are challe...
Self-supervised learning (SSL) has proven vital for advancing research i...
We propose using self-supervised discrete representations for the task o...
Generative spoken language modeling involves learning jointly the acoust...
Natural language (NL) explanations of model predictions are gaining
popu...
We introduce PyText - a deep learning based NLP modeling framework built...