Neural Architecture Search for Speech Emotion Recognition
This work addresses the time-consuming and resource-intensive process of architecture design in speech emotion recognition, offering an incremental improvement for researchers and practitioners in the field.
The paper tackles the problem of manually designing neural architectures for speech emotion recognition by applying neural architecture search (NAS) to automatically configure models, resulting in improved performance from 54.89% to 56.28% on IEMOCAP while maintaining parameter sizes.
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.