Lessons Learnt: Revisit Key Training Strategies for Effective Speech Emotion Recognition in the Wild
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916969040576512 |
|---|---|
| author | Tzeng, Jing-Tong Su, Bo-Hao Wu, Ya-Tse Chou, Hsing-Hang Lee, Chi-Chun |
| author_facet | Tzeng, Jing-Tong Su, Bo-Hao Wu, Ya-Tse Chou, Hsing-Hang Lee, Chi-Chun |
| contents | In this study, we revisit key training strategies in machine learning often overlooked in favor of deeper architectures. Specifically, we explore balancing strategies, activation functions, and fine-tuning techniques to enhance speech emotion recognition (SER) in naturalistic conditions. Our findings show that simple modifications improve generalization with minimal architectural changes. Our multi-modal fusion model, integrating these optimizations, achieves a valence CCC of 0.6953, the best valence score in Task 2: Emotional Attribute Regression. Notably, fine-tuning RoBERTa and WavLM separately in a single-modality setting, followed by feature fusion without training the backbone extractor, yields the highest valence performance. Additionally, focal loss and activation functions significantly enhance performance without increasing complexity. These results suggest that refining core components, rather than deepening models, leads to more robust SER in-the-wild. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_07282 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Lessons Learnt: Revisit Key Training Strategies for Effective Speech Emotion Recognition in the Wild Tzeng, Jing-Tong Su, Bo-Hao Wu, Ya-Tse Chou, Hsing-Hang Lee, Chi-Chun Audio and Speech Processing In this study, we revisit key training strategies in machine learning often overlooked in favor of deeper architectures. Specifically, we explore balancing strategies, activation functions, and fine-tuning techniques to enhance speech emotion recognition (SER) in naturalistic conditions. Our findings show that simple modifications improve generalization with minimal architectural changes. Our multi-modal fusion model, integrating these optimizations, achieves a valence CCC of 0.6953, the best valence score in Task 2: Emotional Attribute Regression. Notably, fine-tuning RoBERTa and WavLM separately in a single-modality setting, followed by feature fusion without training the backbone extractor, yields the highest valence performance. Additionally, focal loss and activation functions significantly enhance performance without increasing complexity. These results suggest that refining core components, rather than deepening models, leads to more robust SER in-the-wild. |
| title | Lessons Learnt: Revisit Key Training Strategies for Effective Speech Emotion Recognition in the Wild |
| topic | Audio and Speech Processing |
| url | https://arxiv.org/abs/2508.07282 |