This paper explores grading text-based audio retrieval relevances with
c...
Speech representation learning with self-supervised algorithms has resul...
Self-supervised techniques for learning speech representations have been...
In this paper, we show that representations capturing syllabic units eme...
The recently-developed infant wearable MAIJU provides a means to
automat...
Modelling of early language acquisition aims to understand how infants
b...
This paper investigates negative sampling for contrastive learning in th...
When domain experts are needed to perform data annotation for complex
ma...
While multi-agent reinforcement learning has been used as an effective m...
Decades of research has studied how language learning infants learn to
d...
Imprecise vowel articulation can be observed in people with Parkinson's
...
We present the visually-grounded language modelling track that was intro...
Infant motility assessment using intelligent wearables is a promising ne...
Researchers have recently started to study how the emotional speech hear...
Unsupervised spoken term discovery (UTD) aims at finding recurring segme...
Neural network models using predictive coding are interesting from the
v...
Infant's spontaneous movements mirror integrity of brain networks, and t...
Earlier research has suggested that human infants might use statistical
...
Automatic syllable count estimation (SCE) is used in a variety of
applic...
Phonemic segmentation of speech is a critical step of speech recognition...