Self-Assessed Affect Recognition Using Fusion of Attentional BLSTM and Static Acoustic Features

Bo-Hao Su, Sung-Lin Yeh, Ming-Ya Ko, Huan-Yu Chen, Shun-Chang Zhong, Jeng-Lin Li, Chi-Chun Lee


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.


 DOI: 10.21437/Interspeech.2018-2261

Cite as: Su, B., Yeh, S., Ko, M., Chen, H., Zhong, S., Li, J., Lee, 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{Su2018,
  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},
  url={http://dx.doi.org/10.21437/Interspeech.2018-2261}
}