Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.25495 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918321775968256 |
|---|---|
| author | Shi, Jiacheng Du, Hongfei Hong, Y. Alicia Gao, Ye |
| author_facet | Shi, Jiacheng Du, Hongfei Hong, Y. Alicia Gao, Ye |
| contents | Speech emotion recognition (SER) with audio-language models (ALMs) remains vulnerable to distribution shifts at test time, leading to performance degradation in out-of-domain scenarios. Test-time adaptation (TTA) provides a promising solution but often relies on gradient-based updates or prompt tuning, limiting flexibility and practicality. We propose Emo-TTA, a lightweight, training-free adaptation framework that incrementally updates class-conditional statistics via an Expectation-Maximization procedure for explicit test-time distribution estimation, using ALM predictions as priors. Emo-TTA operates on individual test samples without modifying model weights. Experiments on six out-of-domain SER benchmarks show consistent accuracy improvements over prior TTA baselines, demonstrating the effectiveness of statistical adaptation in aligning model predictions with evolving test distributions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_25495 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | EMO-TTA: Improving Test-Time Adaptation of Audio-Language Models for Speech Emotion Recognition Shi, Jiacheng Du, Hongfei Hong, Y. Alicia Gao, Ye Sound Artificial Intelligence Speech emotion recognition (SER) with audio-language models (ALMs) remains vulnerable to distribution shifts at test time, leading to performance degradation in out-of-domain scenarios. Test-time adaptation (TTA) provides a promising solution but often relies on gradient-based updates or prompt tuning, limiting flexibility and practicality. We propose Emo-TTA, a lightweight, training-free adaptation framework that incrementally updates class-conditional statistics via an Expectation-Maximization procedure for explicit test-time distribution estimation, using ALM predictions as priors. Emo-TTA operates on individual test samples without modifying model weights. Experiments on six out-of-domain SER benchmarks show consistent accuracy improvements over prior TTA baselines, demonstrating the effectiveness of statistical adaptation in aligning model predictions with evolving test distributions. |
| title | EMO-TTA: Improving Test-Time Adaptation of Audio-Language Models for Speech Emotion Recognition |
| topic | Sound Artificial Intelligence |
| url | https://arxiv.org/abs/2509.25495 |