English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Given the strong results of self-supervised models on various tasks, therehave been surprisingly few studies exploring self-supervised representationsfor acoustic word embeddings (AWE), fixed-dimensional vectors representingvariable-length spoken word segments. In this work, we study severalpre-trained models and pooling methods for constructing AWEs withself-supervised representations. Owing to the contextualized nature ofself-supervised representations, we hypothesize that simple pooling methods,such as averaging, might already be useful for constructing AWEs. Whenevaluating on a standard word discrimination task, we find that HuBERTrepresentations with mean-pooling rival the state of the art on English AWEs.More surprisingly, despite being trained only on English, HuBERTrepresentations evaluated on Xitsonga, Mandarin, and French consistentlyoutperform the multilingual model XLSR-53 (as well as Wav2Vec 2.0 trained onEnglish).

Analyzing Acoustic Word Embeddings from Pre-trained Self-supervised Speech Models