# EMO-TTA: Improving Test-Time Adaptation of Audio-Language Models for Speech Emotion Recognition

arXiv: https://arxiv.org/abs/2509.25495 · HTML: https://mlsanity.com/paper/2509.25495/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 30 references that are in the map.
- First posted on arXiv 29 Sep 2025.

## Builds on (most cited first, 21 of 21)

- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Conditional Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2203.05557/) (2022)
- [Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation](https://mlsanity.com/paper/2211.06687/) (2022)
- [MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations](https://mlsanity.com/paper/1810.02508/) (2018)
- [PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition](https://mlsanity.com/paper/1912.10211/) (2019)
- [Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models](https://mlsanity.com/paper/2209.07511/) (2022)
- [Pengi: An Audio Language Model for Audio Tasks](https://mlsanity.com/paper/2305.11834/) (2023)
- [Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities](https://mlsanity.com/paper/2402.01831/) (2024)
- [HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection](https://mlsanity.com/paper/2202.00874/) (2022)
- [Align Your Prompts: Test-Time Prompting with Distribution Alignment for Zero-Shot Generalization](https://mlsanity.com/paper/2311.01459/) (2023)
- [On the test-time zero-shot generalization of vision-language models: Do we really need prompt learning?](https://mlsanity.com/paper/2405.02266/) (2024)
- [Frustratingly Easy Test-Time Adaptation of Vision-Language Models](https://mlsanity.com/paper/2405.18330/) (2024)
- [Audio-free Prompt Tuning for Language-Audio Models](https://mlsanity.com/paper/2309.08357/) (2023)
- [Adapting Language-Audio Models as Few-Shot Audio Learners](https://mlsanity.com/paper/2305.17719/) (2023)
- [Investigating the Emergent Audio Classification Ability of ASR Foundation Models](https://mlsanity.com/paper/2311.09363/) (2023)
- [Improving Speech Emotion Recognition in Under-Resourced Languages via Speech-to-Speech Translation with Bootstrapping Data Selection](https://mlsanity.com/paper/2409.10985/) (2024)
- [Domain Adaptation for Contrastive Audio-Language Models](https://mlsanity.com/paper/2402.09585/) (2024)
- [EMO-Codec: An In-Depth Look at Emotion Preservation capacity of Legacy and Neural Codec Models With Subjective and Objective Evaluations](https://mlsanity.com/paper/2407.15458/) (2024)
- [CLEP-DG: Contrastive Learning for Speech Emotion Domain Generalization via Soft Prompt Tuning](https://mlsanity.com/paper/2507.04048/) (2025)
- [Describing emotions with acoustic property prompts for speech emotion recognition](https://mlsanity.com/paper/2211.07737/) (2022)
- [SELM: Enhancing Speech Emotion Recognition for Out-of-Domain Scenarios](https://mlsanity.com/paper/2407.15300/) (2024)

## Built on by (most cited first, 1 of 1)

- [Drift-Augmented Scoring: Text-Derived Noise Robustness for Zero-Shot Audio-Language Classification](https://mlsanity.com/paper/2606.04844/) (2026)

## Abstract (arXiv)

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.