# A cross-corpus study on speech emotion recognition

arXiv: https://arxiv.org/abs/2207.02104 · HTML: https://mlsanity.com/paper/2207.02104/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 50 references that are in the map.
- First posted on arXiv 5 Jul 2022.

## Builds on (most cited first, 5 of 5)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Dual Attention Networks for Multimodal Reasoning and Matching](https://mlsanity.com/paper/1611.00471/) (2016)
- [Domain Adversarial for Acoustic Emotion Recognition](https://mlsanity.com/paper/1804.07690/) (2018)
- [Towards Speech Emotion Recognition "in the wild" using Aggregated Corpora and Deep Multi-Task Learning](https://mlsanity.com/paper/1708.03920/) (2017)

## Built on by (most cited first, 7 of 7)

- [VoxEmo: Benchmarking Speech Emotion Recognition with Speech LLMs](https://mlsanity.com/paper/2603.08936/) (2026)
- [A Novel Hybrid Deep Learning Technique for Speech Emotion Detection using Feature Engineering](https://mlsanity.com/paper/2507.07046/) (2025)
- [Domain Adapting Deep Reinforcement Learning for Real-world Speech Emotion Recognition](https://mlsanity.com/paper/2207.12248/) (2022)
- [Empirical Interpretation of the Relationship Between Speech Acoustic Context and Emotion Recognition](https://mlsanity.com/paper/2306.17500/) (2023)
- [Unrequited Emotions: Investigating the Gaps in Motivation and Practice in Speech Emotion Recognition Research](https://mlsanity.com/paper/2604.25776/) (2026)
- [What the Waveform Knows: Transparent-first Speech and Audio Intelligence with Caption Studio](https://mlsanity.com/paper/2607.18704/) (2026)
- [How Far Do Foundation Models Transfer to Infant Signals? A Cross-Dataset Transfer Audit with a Unified Need Ontology](https://mlsanity.com/paper/2608.08989/) (2026)

## Abstract (arXiv)

For speech emotion datasets, it has been difficult to acquire large quantities of reliable data and acted emotions may be over the top compared to less expressive emotions displayed in everyday life. Lately, larger datasets with natural emotions have been created. Instead of ignoring smaller, acted datasets, this study investigates whether information learnt from acted emotions is useful for detecting natural emotions. Cross-corpus research has mostly considered cross-lingual and even cross-age datasets, and difficulties arise from different methods of annotating emotions causing a drop in performance. To be consistent, four adult English datasets covering acted, elicited and natural emotions are considered. A state-of-the-art model is proposed to accurately investigate the degradation of performance. The system involves a bi-directional LSTM with an attention mechanism to classify emotions across datasets. Experiments study the effects of training models in a cross-corpus and multi-domain fashion and results show the transfer of information is not successful. Out-of-domain models, followed by adapting to the missing dataset, and domain adversarial training (DAT) are shown to be more suitable to generalising to emotions across datasets. This shows positive information transfer from acted datasets to those with more natural emotions and the benefits from training on different corpora.