In this study, we present a computational framework to participate in the Self-Assessed Affect Sub-Challenge in the INTERSPEECH 2018 Computation Paralinguistics Challenge. The goal of this sub-challenge is to classify the valence scores given by the speaker themselves into three different levels, i.e., low, medium and high. We explore fusion of Bi-directional LSTM with baseline SVM models to improve the recognition accuracy. In specifics, we extract frame-level acoustic LLDs as input to the BLSTM with a modified attention mechanism and separate SVMs are trained using the standard ComParE_16 baseline feature sets with minority class upsampling. These diverse prediction results are then further fused using a decision-level score fusion scheme to integrate all of the developed models. Our proposed approach achieves a 62.94% and 67.04% unweighted average recall (UAR), which is an 6.24% and 1.04% absolute improvement over the best baseline provided by the challenge organizer. We further provide a detailed comparison analysis between different models.
Cite as: Su, B.-H., Yeh, S.-L., Ko, M.-Y., Chen, H.-Y., Zhong, S.-C., Li, J.-L., Lee, C.-C. (2018) Self-Assessed Affect Recognition Using Fusion of Attentional BLSTM and Static Acoustic Features. Proc. Interspeech 2018, 536-540, doi: 10.21437/Interspeech.2018-2261
@inproceedings{su18d_interspeech, author={Bo-Hao Su and Sung-Lin Yeh and Ming-Ya Ko and Huan-Yu Chen and Shun-Chang Zhong and Jeng-Lin Li and Chi-Chun Lee}, title={{Self-Assessed Affect Recognition Using Fusion of Attentional BLSTM and Static Acoustic Features}}, year=2018, booktitle={Proc. Interspeech 2018}, pages={536--540}, doi={10.21437/Interspeech.2018-2261} }