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

Multimodal emotion recognition (MER) is a fundamental complex researchproblem due to the uncertainty of human emotional expression and theheterogeneity gap between different modalities. Audio and text modalities areparticularly important for a human participant in understanding emotions.Although many successful attempts have been designed multimodal representationsfor MER, there still exist multiple challenges to be addressed: 1) bridging theheterogeneity gap between multimodal features and model inter- and intra-modalinteractions of multiple modalities; 2) effectively and efficiently modellingthe contextual dynamics in the conversation sequence. In this paper, we proposeCross-Modal RoBERTa (CM-RoBERTa) model for emotion detection from spoken audioand corresponding transcripts. As the core unit of the CM-RoBERTa, parallelself- and cross- attention is designed to dynamically capture inter- andintra-modal interactions of audio and text. Specially, the mid-level fusion andresidual module are employed to model long-term contextual dependencies andlearn modality-specific patterns. We evaluate the approach on the MELD datasetand the experimental results show the proposed approach achieves thestate-of-art performance on the dataset.

cross-modal fusion techniques for utterance-level emotion recognition from text and speech