# Multi-Scale Temporal Transformer For Speech Emotion Recognition

arXiv: https://arxiv.org/abs/2410.00390 · HTML: https://mlsanity.com/paper/2410.00390/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Oct 2024.

## Built on by (most cited first, 4 of 4)

- [4DEquine: Disentangling Motion and Appearance for 4D Equine Reconstruction from Monocular Video](https://mlsanity.com/paper/2603.10125/) (2026)
- [Balancing Task-invariant Interaction and Task-specific Adaptation for Unified Image Fusion](https://mlsanity.com/paper/2504.05164/) (2025)
- [PTS-SNN: A Prompt-Tuned Temporal Shift Spiking Neural Networks for Efficient Speech Emotion Recognition](https://mlsanity.com/paper/2602.08240/) (2026)
- [Enriching Speech Emotion Representations with Conversational Context](https://mlsanity.com/paper/2609.26422/) (2026)

## Abstract (arXiv)

Speech emotion recognition plays a crucial role in human-machine interaction systems. Recently various optimized Transformers have been successfully applied to speech emotion recognition. However, the existing Transformer architectures focus more on global information and require large computation. On the other hand, abundant speech emotional representations exist locally on different parts of the input speech. To tackle these problems, we propose a Multi-Scale TRansfomer (MSTR) for speech emotion recognition. It comprises of three main components: (1) a multi-scale temporal feature operator, (2) a fractal self-attention module, and (3) a scale mixer module. These three components can effectively enhance the transformer's ability to learn multi-scale local emotion representations. Experimental results demonstrate that the proposed MSTR model significantly outperforms a vanilla Transformer and other state-of-the-art methods across three speech emotion datasets: IEMOCAP, MELD and, CREMAD. In addition, it can greatly reduce the computational cost.