# A study on cross-corpus speech emotion recognition and data augmentation

arXiv: https://arxiv.org/abs/2201.03511 · HTML: https://mlsanity.com/paper/2201.03511/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 25 references that are in the map.
- First posted on arXiv 10 Jan 2022.

## Builds on (most cited first, 7 of 7)

- [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)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [Dual Attention Networks for Multimodal Reasoning and Matching](https://mlsanity.com/paper/1611.00471/) (2016)
- [Multi-attention Recurrent Network for Human Communication Comprehension](https://mlsanity.com/paper/1802.00923/) (2018)
- [Domain Adversarial for Acoustic Emotion Recognition](https://mlsanity.com/paper/1804.07690/) (2018)
- [Conversational Emotion Analysis via Attention Mechanisms](https://mlsanity.com/paper/1910.11263/) (2019)

## Built on by (most cited first, 5 of 5)

- [Deep Transfer Learning for Automatic Speech Recognition: Towards Better Generalization](https://mlsanity.com/paper/2304.14535/) (2023)
- [More Similar than Dissimilar: Modeling Annotators for Cross-Corpus Speech Emotion Recognition](https://mlsanity.com/paper/2509.12295/) (2025)
- [Leveraging Cross-Attention Transformer and Multi-Feature Fusion for Cross-Linguistic Speech Emotion Recognition](https://mlsanity.com/paper/2501.10408/) (2025)
- [Emotion-Disentangled Embedding Alignment for Noise-Robust and Cross-Corpus Speech Emotion Recognition](https://mlsanity.com/paper/2510.09072/) (2025)
- [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)

Models that can handle a wide range of speakers and acoustic conditions are essential in speech emotion recognition (SER). Often, these models tend to show mixed results when presented with speakers or acoustic conditions that were not visible during training. This paper investigates the impact of cross-corpus data complementation and data augmentation on the performance of SER models in matched (test-set from same corpus) and mismatched (test-set from different corpus) conditions. Investigations using six emotional speech corpora that include single and multiple speakers as well as variations in emotion style (acted, elicited, natural) and recording conditions are presented. Observations show that, as expected, models trained on single corpora perform best in matched conditions while performance decreases between 10-40% in mismatched conditions, depending on corpus specific features. Models trained on mixed corpora can be more stable in mismatched contexts, and the performance reductions range from 1 to 8% when compared with single corpus models in matched conditions. Data augmentation yields additional gains up to 4% and seem to benefit mismatched conditions more than matched ones.