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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Many recent studies have focused on fine-tuning pre-trained models for speechemotion recognition (SER), resulting in promising performance compared totraditional methods that rely largely on low-level, knowledge-inspired acousticfeatures. These pre-trained speech models learn general-purpose speechrepresentations using self-supervised or weakly-supervised learning objectivesfrom large-scale datasets. Despite the significant advances made in SER throughthe use of pre-trained architecture, fine-tuning these large pre-trained modelsfor different datasets requires saving copies of entire weight parameters,rendering them impractical to deploy in real-world settings. As an alternative,this work explores parameter-efficient fine-tuning (PEFT) approaches foradapting pre-trained speech models for emotion recognition. Specifically, weevaluate the efficacy of adapter tuning, embedding prompt tuning, and LoRa(Low-rank approximation) on four popular SER testbeds. Our results reveal thatLoRa achieves the best fine-tuning performance in emotion recognition whileenhancing fairness and requiring only a minimal extra amount of weightparameters. Furthermore, our findings offer novel insights into future researchdirections in SER, distinct from existing approaches focusing on directlyfine-tuning the model architecture. Our code is publicly available under:https://github.com/usc-sail/peft-ser.

PEFT-SER: On the Use of Parameter Efficient Transfer Learning Approaches For Speech Emotion Recognition Using Pre-trained Speech Models