Self-supervised learning (SSL) has allowed substantial progress in Autom...
Word or word-fragment based Language Models (LM) are typically preferred...
Finding word boundaries in continuous speech is challenging as there is
...
We introduce a simple neural encoder architecture that can be trained us...
We introduce dGSLM, the first "textless" model able to generate audio sa...
We present the Zero Resource Speech Challenge 2020, which aims at learni...
Speech embeddings are fixed-size acoustic representations of variable-le...
We present the Zero Resource Speech Challenge 2019, which proposes to bu...