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

Self-supervised learning leverages unlabeled data effectively, improvinglabel efficiency and generalization to domains without labeled data. Whilerecent work has studied generalization to more acoustic/linguistic domains,languages, and modalities, these investigations are limited to single-sourcespeech with one primary speaker in the recording. This paper presents CocktailHuBERT, a self-supervised learning framework that generalizes to mixture speechusing a masked pseudo source separation objective. This objective encouragesthe model to identify the number of sources, separate and understand thecontext, and infer the content of masked regions represented as discoveredunits. Cocktail HuBERT outperforms state-of-the-art results with 69% lower WERon multi-speaker ASR, 31% lower DER on diarization, and is competitive onsingle- and multi-speaker tasks from SUPERB.

Cocktail HuBERT: Generalized Self-Supervised Pre-training for Mixture and Single-Source Speech