# Learning Robust Self-attention Features for Speech Emotion Recognition with Label-adaptive Mixup

arXiv: https://arxiv.org/abs/2305.06273 · HTML: https://mlsanity.com/paper/2305.06273/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 25 references that are in the map.
- First posted on arXiv 7 May 2023.

## Builds on (most cited first, 10 of 10)

- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [Libri-Light: A Benchmark for ASR with Limited or No Supervision](https://mlsanity.com/paper/1912.07875/) (2019)
- [Speech Emotion Recognition using Self-Supervised Features](https://mlsanity.com/paper/2202.03896/) (2022)
- [Speech Emotion Recognition with Co-Attention based Multi-level Acoustic Information](https://mlsanity.com/paper/2203.15326/) (2022)
- [Emotion recognition by fusing time synchronous and time asynchronous representations](https://mlsanity.com/paper/2010.14102/) (2020)
- [Emotion Recognition From Speech With Recurrent Neural Networks](https://mlsanity.com/paper/1701.08071/) (2017)
- [Neural Architecture Search for Speech Emotion Recognition](https://mlsanity.com/paper/2203.16928/) (2022)
- [Speech Emotion Recognition with Global-Aware Fusion on Multi-scale Feature Representation](https://mlsanity.com/paper/2204.05571/) (2022)

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

- [Missing-by-Design: Certifiable Modality Deletion for Revocable Multimodal Sentiment Analysis](https://mlsanity.com/paper/2602.16144/) (2026)
- [Emotion Collider: Dual Hyperbolic Mirror Manifolds for Sentiment Recovery via Anti Emotion Reflection](https://mlsanity.com/paper/2602.16161/) (2026)
- [ModalImmune: Immunity Driven Unlearning via Self Destructive Training](https://mlsanity.com/paper/2602.16197/) (2026)
- [Revisiting Interpolation Augmentation for Speech-to-Text Generation](https://mlsanity.com/paper/2406.15846/) (2024)
- [Multi-Loss Learning for Speech Emotion Recognition with Energy-Adaptive Mixup and Frame-Level Attention](https://mlsanity.com/paper/2512.04551/) (2025)

## Abstract (arXiv)

Speech Emotion Recognition (SER) is to recognize human emotions in a natural verbal interaction scenario with machines, which is considered as a challenging problem due to the ambiguous human emotions. Despite the recent progress in SER, state-of-the-art models struggle to achieve a satisfactory performance. We propose a self-attention based method with combined use of label-adaptive mixup and center loss. By adapting label probabilities in mixup and fitting center loss to the mixup training scheme, our proposed method achieves a superior performance to the state-of-the-art methods.