Saved in:
Bibliographic Details
Main Authors: Shi, Jiacheng, Zhang, Yanfu, Gao, Ye
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.04048
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916828917268480
author Shi, Jiacheng
Zhang, Yanfu
Gao, Ye
author_facet Shi, Jiacheng
Zhang, Yanfu
Gao, Ye
contents Speech Emotion Recognition (SER) is fundamental to affective computing and human-computer interaction, yet existing models struggle to generalize across diverse acoustic conditions. While Contrastive Language-Audio Pretraining (CLAP) provides strong multimodal alignment, it lacks dedicated mechanisms for capturing emotional cues, making it suboptimal for SER. To address this, we propose CLEP-DG, a framework that enhances CLAP's robustness in emotion recognition. First, we fine-tune CLAP to obtain CLEP, adapting it on large-scale emotional speech datasets to better encode emotion-relevant features. Then, we introduce Acoustic Context Prompt Tuning (ACPT), a text-driven augmentation strategy that optimizes learnable prompt vectors to model diverse acoustic environments without additional labeled audio. Finally, leveraging cross-modal transferability, we train a classifier on text-derived embeddings and apply it to the audio encoder during inference, mitigating domain shifts between textual supervision and audio-based emotion recognition. Experiments across five benchmark datasets show that CLEP-DG outperforms prior CLAP-based approaches, achieving state-of-the-art performance in both supervised and domain generalization settings.
format Preprint
id arxiv_https___arxiv_org_abs_2507_04048
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CLEP-DG: Contrastive Learning for Speech Emotion Domain Generalization via Soft Prompt Tuning
Shi, Jiacheng
Zhang, Yanfu
Gao, Ye
Sound
Audio and Speech Processing
Speech Emotion Recognition (SER) is fundamental to affective computing and human-computer interaction, yet existing models struggle to generalize across diverse acoustic conditions. While Contrastive Language-Audio Pretraining (CLAP) provides strong multimodal alignment, it lacks dedicated mechanisms for capturing emotional cues, making it suboptimal for SER. To address this, we propose CLEP-DG, a framework that enhances CLAP's robustness in emotion recognition. First, we fine-tune CLAP to obtain CLEP, adapting it on large-scale emotional speech datasets to better encode emotion-relevant features. Then, we introduce Acoustic Context Prompt Tuning (ACPT), a text-driven augmentation strategy that optimizes learnable prompt vectors to model diverse acoustic environments without additional labeled audio. Finally, leveraging cross-modal transferability, we train a classifier on text-derived embeddings and apply it to the audio encoder during inference, mitigating domain shifts between textual supervision and audio-based emotion recognition. Experiments across five benchmark datasets show that CLEP-DG outperforms prior CLAP-based approaches, achieving state-of-the-art performance in both supervised and domain generalization settings.
title CLEP-DG: Contrastive Learning for Speech Emotion Domain Generalization via Soft Prompt Tuning
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2507.04048