Self-supervised techniques for learning speech representations have been...
Modelling of early language acquisition aims to understand how infants
b...
Most automatic speech processing systems are sensitive to the acoustic
e...
We present the visually-grounded language modelling track that was intro...
We introduce Seshat, a new, simple and open-source software to efficient...
This paper presents the problems and solutions addressed at the JSALT
wo...
This paper introduces the second DIHARD challenge, the second in a serie...
We investigate whether infant-directed speech (IDS) could facilitate wor...