{"ID":2898138,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.04048","arxiv_id":"2507.04048","title":"CLEP-DG: Contrastive Learning for Speech Emotion Domain Generalization via Soft Prompt Tuning","abstract":"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.","short_abstract":"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 emot...","url_abs":"https://arxiv.org/abs/2507.04048","url_pdf":"https://arxiv.org/pdf/2507.04048v1","authors":"[\"Jiacheng Shi\",\"Yanfu Zhang\",\"Ye Gao\"]","published":"2025-07-05T14:16:06Z","proceeding":"cs.SD","tasks":"[\"cs.SD\",\"eess.AS\"]","methods":"[]","has_code":false}