# Speech Emotion Recognition via Contrastive Loss under Siamese Networks

arXiv: https://arxiv.org/abs/1910.11174 · HTML: https://mlsanity.com/paper/1910.11174/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Oct 2019.

## Built on by (most cited first, 10 of 10)

- [GCNet: Graph Completion Network for Incomplete Multimodal Learning in Conversation](https://mlsanity.com/paper/2203.02177/) (2022)
- [Predicting Human Card Selection in Magic: The Gathering with Contextual Preference Ranking](https://mlsanity.com/paper/2105.11864/) (2021)
- [Deep Clustering via Center-Oriented Margin Free-Triplet Loss for Skin Lesion Detection in Highly Imbalanced Datasets](https://mlsanity.com/paper/2204.02275/) (2022)
- [Few-shot Learning in Emotion Recognition of Spontaneous Speech Using a Siamese Neural Network with Adaptive Sample Pair Formation](https://mlsanity.com/paper/2109.02915/) (2021)
- [N-shot Palm Vein Verification Using Siamese Networks](https://mlsanity.com/paper/2109.12808/) (2021)
- [EmotionNAS: Two-stream Neural Architecture Search for Speech Emotion Recognition](https://mlsanity.com/paper/2203.13617/) (2022)
- [Efficient Labelling of Affective Video Datasets via Few-Shot & Multi-Task Contrastive Learning](https://mlsanity.com/paper/2308.02173/) (2023)
- [A Weakly Supervised Approach to Emotion-change Prediction and Improved Mood Inference](https://mlsanity.com/paper/2306.06979/) (2023)
- [DSNet: Disentangled Siamese Network with Neutral Calibration for Speech Emotion Recognition](https://mlsanity.com/paper/2312.15593/) (2023)
- [Deep Insights into Cognitive Decline: A Survey of Leveraging Non-Intrusive Modalities with Deep Learning Techniques](https://mlsanity.com/paper/2410.18972/) (2024)

## Abstract (arXiv)

Speech emotion recognition is an important aspect of human-computer interaction. Prior work proposes various end-to-end models to improve the classification performance. However, most of them rely on the cross-entropy loss together with softmax as the supervision component, which does not explicitly encourage discriminative learning of features. In this paper, we introduce the contrastive loss function to encourage intra-class compactness and inter-class separability between learnable features. Furthermore, multiple feature selection methods and pairwise sample selection methods are evaluated. To verify the performance of the proposed system, we conduct experiments on The Interactive Emotional Dyadic Motion Capture (IEMOCAP) database, a common evaluation corpus. Experimental results reveal the advantages of the proposed method, which reaches 62.19% in the weighted accuracy and 63.21% in the unweighted accuracy. It outperforms the baseline system that is optimized without the contrastive loss function with 1.14% and 2.55% in the weighted accuracy and the unweighted accuracy, respectively.