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

In this paper, we show that representations capturing syllabic units emergewhen training a self-supervised speech model with a visually-grounded trainingobjective. We demonstrate that a nearly identical model architecture (HuBERT)trained with a masked language modeling loss does not exhibit this sameability, suggesting that the visual grounding objective is responsible for theemergence of this phenomenon. We propose the use of a minimum cut algorithm toautomatically predict syllable boundaries in speech, followed by a 2-stageclustering method to group identical syllables together. We show that our modelnot only outperforms a state-of-the-art syllabic segmentation method on thelanguage it was trained on (English), but also generalizes in a zero-shotfashion to Estonian. Finally, we show that the same model is capable ofzero-shot generalization for a word segmentation task on 4 other languages fromthe Zerospeech Challenge, in some cases beating the previous state-of-the-art.

Syllable Discovery and Cross-Lingual Generalization in a Visually Grounded, Self-Supervised Speech Model