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

Cross-corpus speech emotion recognition (SER) aims to transfer emotionalknowledge from a labeled source corpus to an unlabeled corpus. However, priormethods require access to source data during adaptation, which is unattainablein real-life scenarios due to data privacy protection concerns. This papertackles a more practical task, namely source-free cross-corpus SER, where apre-trained source model is adapted to the target domain without access tosource data. To address the problem, we propose a novel method calledemotion-aware contrastive adaptation network (ECAN). The core idea is tocapture local neighborhood information between samples while considering theglobal class-level adaptation. Specifically, we propose a nearest neighborcontrastive learning to promote local emotion consistency among features ofhighly similar samples. Furthermore, relying solely on nearest neighborhoodsmay lead to ambiguous boundaries between clusters. Thus, we incorporatesupervised contrastive learning to encourage greater separation betweenclusters representing different emotions, thereby facilitating improvedclass-level adaptation. Extensive experiments indicate that our proposed ECANsignificantly outperforms state-of-the-art methods under the source-freecross-corpus SER setting on several speech emotion corpora.

Emotion-Aware Contrastive Adaptation Network for Source-Free Cross-Corpus Speech Emotion Recognition