Analyzing Acoustic Word Embeddings from Pre-trained Self-supervised Speech Models. (arXiv:2210.16043v1 [cs.CL])

Given the strong results of self-supervised models on various tasks, there
have been surprisingly few studies exploring self-supervised representations
for acoustic word embeddings (AWE), fixed-dimensional vectors representing
variable-length spoken word segments. In this work, we study several
pre-trained models and pooling methods for constructing AWEs with
self-supervised representations. Owing to the contextualized nature of
self-supervised representations, we hypothesize that simple pooling methods,
such as averaging, might already be useful for constructing AWEs. When
evaluating on a standard word discrimination task, …

arxiv speech word embeddings