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

Despite recent advancements in speech emotion recognition (SER) models,state-of-the-art deep learning (DL) approaches face the challenge of thelimited availability of annotated data. Large language models (LLMs) haverevolutionised our understanding of natural language, introducing emergentproperties that broaden comprehension in language, speech, and vision. Thispaper examines the potential of LLMs to annotate abundant speech data, aimingto enhance the state-of-the-art in SER. We evaluate this capability acrossvarious settings using publicly available speech emotion classificationdatasets. Leveraging ChatGPT, we experimentally demonstrate the promising roleof LLMs in speech emotion data annotation. Our evaluation encompassessingle-shot and few-shots scenarios, revealing performance variability in SER.Notably, we achieve improved results through data augmentation, incorporatingChatGPT-annotated samples into existing datasets. Our work uncovers newfrontiers in speech emotion classification, highlighting the increasingsignificance of LLMs in this field moving forward.

Can Large Language Models Aid in Annotating Speech Emotional Data? Uncovering New Frontiers