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

Speech representation learning plays a vital role in speech processing. Amongthem, self-supervised learning (SSL) has become an important researchdirection. It has been shown that an SSL pretraining model can achieveexcellent performance in various downstream tasks of speech processing. On theother hand, supervised multi-task learning (MTL) is another representationlearning paradigm, which has been proven effective in computer vision (CV) andnatural language processing (NLP). However, there is no systematic research onthe general representation learning model trained by supervised MTL in speechprocessing. In this paper, we show that MTL finetuning can further improve SSLpretraining. We analyze the generalizability of supervised MTL finetuning toexamine if the speech representation learned by MTL finetuning can generalizeto unseen new tasks.

Speech Representation Learning Through Self-supervised Pretraining And Multi-task Finetuning