# Neural Architecture Search for Speech Emotion Recognition

arXiv: https://arxiv.org/abs/2203.16928 · HTML: https://mlsanity.com/paper/2203.16928/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 35 references that are in the map.
- First posted on arXiv 31 Mar 2022.

## Builds on (most cited first, 19 of 19)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [DARTS: Differentiable Architecture Search](https://mlsanity.com/paper/1806.09055/) (2018)
- [Neural Architecture Search with Reinforcement Learning](https://mlsanity.com/paper/1611.01578/) (2016)
- [Learning Transferable Architectures for Scalable Image Recognition](https://mlsanity.com/paper/1707.07012/) (2017)
- [Regularized Evolution for Image Classifier Architecture Search](https://mlsanity.com/paper/1802.01548/) (2018)
- [Efficient Neural Architecture Search via Parameter Sharing](https://mlsanity.com/paper/1802.03268/) (2018)
- [Single Path One-Shot Neural Architecture Search with Uniform Sampling](https://mlsanity.com/paper/1904.00420/) (2019)
- [Large-Scale Evolution of Image Classifiers](https://mlsanity.com/paper/1703.01041/) (2017)
- [Attentional Pooling for Action Recognition](https://mlsanity.com/paper/1711.01467/) (2017)
- [Efficient Neural Architecture Search via Proximal Iterations](https://mlsanity.com/paper/1905.13577/) (2019)
- [LightSpeech: Lightweight and Fast Text to Speech with Neural Architecture Search](https://mlsanity.com/paper/2102.04040/) (2021)
- [Speech Emotion Recognition with Dual-Sequence LSTM Architecture](https://mlsanity.com/paper/1910.08874/) (2019)
- [DARTS-ASR: Differentiable Architecture Search for Multilingual Speech Recognition and Adaptation](https://mlsanity.com/paper/2005.07029/) (2020)
- [Neural Architecture Search For LF-MMI Trained Time Delay Neural Networks](https://mlsanity.com/paper/2201.03943/) (2022)
- [Darts-Conformer: Towards Efficient Gradient-Based Neural Architecture Search For End-to-End ASR](https://mlsanity.com/paper/2104.02868/) (2021)
- [Efficient Neural Architecture Search for End-to-end Speech Recognition via Straight-Through Gradients](https://mlsanity.com/paper/2011.05649/) (2020)
- [Improved Conformer-based End-to-End Speech Recognition Using Neural Architecture Search](https://mlsanity.com/paper/2104.05390/) (2021)
- [Learned Transferable Architectures Can Surpass Hand-Designed Architectures for Large Scale Speech Recognition](https://mlsanity.com/paper/2008.11589/) (2020)

## Built on by (most cited first, 6 of 6)

- [Resource-Efficient Separation Transformer](https://mlsanity.com/paper/2206.09507/) (2022)
- [EC-NAS: Energy Consumption Aware Tabular Benchmarks for Neural Architecture Search](https://mlsanity.com/paper/2210.06015/) (2022)
- [Learning Robust Self-attention Features for Speech Emotion Recognition with Label-adaptive Mixup](https://mlsanity.com/paper/2305.06273/) (2023)
- [Frame-level emotional state alignment method for speech emotion recognition](https://mlsanity.com/paper/2312.16383/) (2023)
- [Enhancing Speech Emotion Recognition Through Differentiable Architecture Search](https://mlsanity.com/paper/2305.14402/) (2023)
- [emoDARTS: Joint Optimisation of CNN & Sequential Neural Network Architectures for Superior Speech Emotion Recognition](https://mlsanity.com/paper/2403.14083/) (2024)

## Abstract (arXiv)

Deep neural networks have brought significant advancements to speech emotion recognition (SER). However, the architecture design in SER is mainly based on expert knowledge and empirical (trial-and-error) evaluations, which is time-consuming and resource intensive. In this paper, we propose to apply neural architecture search (NAS) techniques to automatically configure the SER models. To accelerate the candidate architecture optimization, we propose a uniform path dropout strategy to encourage all candidate architecture operations to be equally optimized. Experimental results of two different neural structures on IEMOCAP show that NAS can improve SER performance (54.89% to 56.28%) while maintaining model parameter sizes. The proposed dropout strategy also shows superiority over the previous approaches.