Variational Autoencoders for Learning Latent Representations of Speech Emotion: A Preliminary Study

23 Dec 2017  ·  Siddique Latif, Rajib Rana, Junaid Qadir, Julien Epps ·

Learning the latent representation of data in unsupervised fashion is a very interesting process that provides relevant features for enhancing the performance of a classifier. For speech emotion recognition tasks, generating effective features is crucial. Currently, handcrafted features are mostly used for speech emotion recognition, however, features learned automatically using deep learning have shown strong success in many problems, especially in image processing. In particular, deep generative models such as Variational Autoencoders (VAEs) have gained enormous success for generating features for natural images. Inspired by this, we propose VAEs for deriving the latent representation of speech signals and use this representation to classify emotions. To the best of our knowledge, we are the first to propose VAEs for speech emotion classification. Evaluations on the IEMOCAP dataset demonstrate that features learned by VAEs can produce state-of-the-art results for speech emotion classification.

PDF Abstract


Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.


No methods listed for this paper. Add relevant methods here