ISCA Archive Interspeech 2015
ISCA Archive Interspeech 2015

Emotion clustering based on probabilistic linear discriminant analysis

Mahnoosh Mehrabani, Ozlem Kalinli, Ruxin Chen

This study proposes an emotion clustering method based on Probabilistic Linear Discriminant Analysis (PLDA). Each emotional utterance is modeled as a GMM mean supervector. Hierarchical clustering is applied to cluster supervectors that represent similar emotions using a likelihood ratio from a PLDA model. The PLDA model can be trained with a different emotional database from the test data, with different emotion categories, speakers, or even languages. The advantage of using a PLDA model is that it identifies emotion dependent subspaces of the GMM mean supervector space. Our proposed emotion clustering based on PLDA likelihood distance improves 5-emotion clustering accuracy by 37.1% absolute compared to a baseline with Euclidean distance when PLDA model is trained with a separate set of speakers from the same database. Even when PLDA model is trained using a different database with a different language, clustering performance is improved by 11.2%.

doi: 10.21437/Interspeech.2015-327

Cite as: Mehrabani, M., Kalinli, O., Chen, R. (2015) Emotion clustering based on probabilistic linear discriminant analysis. Proc. Interspeech 2015, 1314-1318, doi: 10.21437/Interspeech.2015-327

  author={Mahnoosh Mehrabani and Ozlem Kalinli and Ruxin Chen},
  title={{Emotion clustering based on probabilistic linear discriminant analysis}},
  booktitle={Proc. Interspeech 2015},