Variational autoencoders for learning latent representations of speech emotion: a preliminary study

Latif, Siddique and Rana, Rajib and Qadir, Junaid and Epps, Julien (2018) Variational autoencoders for learning latent representations of speech emotion: a preliminary study. In: Interspeech 2018: Speech Research for Emerging Markets in Multilingual Societies, 2-6 Sept 2018, Hyderabad, India.


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 in 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.

Statistics for USQ ePrint 35635
Statistics for this ePrint Item
Item Type: Conference or Workshop Item (Commonwealth Reporting Category E) (Paper)
Refereed: Yes
Item Status: Live Archive
Additional Information: Copyright 2018 International Speech Communication Association (ISCA).
Faculty/School / Institute/Centre: Current - Institute for Resilient Regions
Date Deposited: 18 Feb 2019 01:20
Last Modified: 05 Apr 2019 04:18
Uncontrolled Keywords: speech emotion classification, variational auto-encoders, deep learning, feature learning
Fields of Research : 08 Information and Computing Sciences > 0806 Information Systems > 080699 Information Systems not elsewhere classified
Socio-Economic Objective: E Expanding Knowledge > 97 Expanding Knowledge > 970108 Expanding Knowledge in the Information and Computing Sciences
Identification Number or DOI: doi:10.21437/Interspeech.2018-1568

Actions (login required)

View Item Archive Repository Staff Only