Unsupervised Representation Learning with Future Observation Prediction for Speech Emotion Recognition

TL;DR

This paper introduces a novel unsupervised learning method combining Future Observation Prediction with transfer learning techniques to improve speech emotion recognition, especially in low-resource scenarios.

Contribution

It proposes integrating FOP with transfer learning for better modeling of long-term dependencies in speech emotion recognition.

Findings

Outperforms existing unsupervised strategies on IEMOCAP

Effective in low-resource speech emotion recognition

Enhances long-term dependency modeling in speech data

Abstract

Prior works on speech emotion recognition utilize various unsupervised learning approaches to deal with low-resource samples. However, these methods pay less attention to modeling the long-term dynamic dependency, which is important for speech emotion recognition. To deal with this problem, this paper combines the unsupervised representation learning strategy -- Future Observation Prediction (FOP), with transfer learning approaches (such as Fine-tuning and Hypercolumns). To verify the effectiveness of the proposed method, we conduct experiments on the IEMOCAP database. Experimental results demonstrate that our method is superior to currently advanced unsupervised learning strategies.